Fluid-1-Mini-2B-MLX-mixed46 / fluiddecode-manifest.json
ALTICDEV's picture
docs: simplify model card licensing notice
f2e4fd5 verified
Raw
History Blame Contribute Delete
248 kB
{
"artifact": {
"bytes": 1391219247,
"file": "model.safetensors",
"sha256": "79b19ac0db1de0e35e0997e2a4e9ece25168416e013b66da2ada585008336e7e",
"tensorCount": 828
},
"configSHA256": "d8f54ac3563d7eb3e160114b82f84b2e211cf4fc88e82626c761cfd750bad06a",
"converter": {
"name": "splice-q4dwq-q6",
"version": "local"
},
"createdAt": "2026-08-21T22:50:36.218447+00:00",
"engineCheck": "none",
"files": [
{
"bytes": 1267,
"file": "ALTIC-MODEL-TERMS.md",
"sha256": "774d6973e678db863d6a3149ccae53c4dc97d9b2f758348b5092c549c282a1de"
},
{
"bytes": 11544,
"file": "LICENSE-QWEN-APACHE-2.0",
"sha256": "bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a"
},
{
"bytes": 559,
"file": "README.md",
"sha256": "76b2008ad3a47def4d6681105593f43dae54daeb4ee8adce1314f369a7c3bb95"
},
{
"bytes": 7755,
"file": "chat_template.jinja",
"sha256": "273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80"
},
{
"bytes": 51066,
"file": "config.json",
"sha256": "d8f54ac3563d7eb3e160114b82f84b2e211cf4fc88e82626c761cfd750bad06a"
},
{
"bytes": 1391219247,
"file": "model.safetensors",
"sha256": "79b19ac0db1de0e35e0997e2a4e9ece25168416e013b66da2ada585008336e7e"
},
{
"bytes": 68799,
"file": "model.safetensors.index.json",
"sha256": "bd9ab3b714b5c90cafe802386f340ef7f6066837bd25362c2fa9dd5c5887419f"
},
{
"bytes": 7000763,
"file": "tokenizer.json",
"sha256": "a327311621c5780b2261e24005fc7b7adf271300594d8e502761cdeb944b0d6c"
},
{
"bytes": 1231,
"file": "tokenizer_config.json",
"sha256": "9bd5d8539cf221dd8e77483d93f6f01c9fc340e13b60fdc10087f046fbebe9a3"
}
],
"metadata": {
"files": [
"README.md"
],
"licenseFiles": [
"ALTIC-MODEL-TERMS.md",
"LICENSE-QWEN-APACHE-2.0"
],
"missingLicenseExplicitlyAllowed": false
},
"profile": "qwen3.5-0.8b-affine-mixed-q4q6-g64-experimental",
"quantization": {
"defaultBits": 4,
"groupSize": 64,
"mode": "affine",
"policy": {
"kind": "custom",
"sha256": "546173ac4d0177c95b621209ec279d0d5e5c6677c3011314f8e94010b5f8c2c5"
},
"prefixes": [
{
"bits": 4,
"bytes": 113246208,
"groupSize": 64,
"prefix": "language_model.model.embed_tokens",
"sha256": "d02dc558e28832019a7f33a74a49e640d274d5fee7637a73ea5d07d1ab18b104",
"tensors": [
{
"bytes": 100663296,
"dtype": "U32",
"name": "language_model.model.embed_tokens.weight",
"sha256": "a274e26dea004385ef8a3be9a0e774ad77ed90c28b3f309aadcc2f329cfe5b74",
"shape": [
98304,
256
]
},
{
"bytes": 6291456,
"dtype": "BF16",
"name": "language_model.model.embed_tokens.scales",
"sha256": "c9cc187b9789c2cb12e755965f87b710a7b761279b0114860fcea5be57fa320a",
"shape": [
98304,
32
]
},
{
"bytes": 6291456,
"dtype": "BF16",
"name": "language_model.model.embed_tokens.biases",
"sha256": "8b27b6313d8d72240014b1cbbdab2f8965d2783f9576a7a528b1104823bc7a1d",
"shape": [
98304,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.0.linear_attn.in_proj_a",
"sha256": "1e13745bc939721930bdadb3bd0949a4f1d3f093695117f1092e431ca1b2fe11",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.0.linear_attn.in_proj_a.weight",
"sha256": "b5b123be90269568488c722e0caf6e89a094ad11276caebd80829b8dc914376c",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_a.scales",
"sha256": "14f6dfcc53f86134a4ba0bb44e513c63936b2dd9e4b8a7e933b45057553eea23",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_a.biases",
"sha256": "9bf214f59055a106b018dd8f0232388b0d7d7ceccab8bba00ee81790af56a782",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.0.linear_attn.in_proj_b",
"sha256": "e4463039454f0177576c5364e19c3394022adfc2e1320e87dad7cc2090519a6d",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.0.linear_attn.in_proj_b.weight",
"sha256": "3eddc3437bdc9a8770f199b85d558e36056ad0cadae7763fde848d0909262833",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_b.scales",
"sha256": "a105234c56575fc0b67f9ddb35a458d85475f7b008c0ae0d0b738be02ec1f65c",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_b.biases",
"sha256": "01d6381a604b879ebf5e666053684782719ce6ff9f88c808a1ab863895b308a3",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.0.linear_attn.in_proj_qkv",
"sha256": "0d82cec0733c21b55180875f265a26425252e481acbe7f961378733e366ef9bc",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.0.linear_attn.in_proj_qkv.weight",
"sha256": "d543cd1e0a2fc272453417e5a6b445d25f826ac060b7165931f49c47eb15697d",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_qkv.scales",
"sha256": "c5955297557f66c193d13a4f2791af931ed2dc549734027a510d917151cad45b",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_qkv.biases",
"sha256": "a93c963eb24fec92ea1e20c03a1d9a0bac7e7593355eeee5c5225faabf14e23b",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.0.linear_attn.in_proj_z",
"sha256": "839343b647dd1acb50b23cfdad4c6e6bebacdd0d4565f0118b84256435691a4c",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.0.linear_attn.in_proj_z.weight",
"sha256": "8f46494b7e900717a82dfb2ab0e9d1b2ce08f5022fb9405974bd0f524e5bb831",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_z.scales",
"sha256": "470751cd5e4d272164308d4453d63c7fac4f982fe19ca865ee90d644396b4df4",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.in_proj_z.biases",
"sha256": "1a68a902c131e472a1e74e666774ad51787fadf278efd288d24a20b282a1e491",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.0.linear_attn.out_proj",
"sha256": "d39a835690374b47008eea3c0ae542155616d0edd557e28607e8f6df9ac28536",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.0.linear_attn.out_proj.weight",
"sha256": "1a352e37d755d8622348c085a97dd8fd005d59b6459ad8434e95228e2d1f2458",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.out_proj.scales",
"sha256": "4399109c1cedeb76ae0243740175650f574e61fbd6dbcbd473309da5f97cb89b",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.0.linear_attn.out_proj.biases",
"sha256": "28f8db971739e02a23965889f4dc12b4473e0551e317c42a3fb0810654c2a5df",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.0.mlp.down_proj",
"sha256": "306271e3eec2fc66d78cd10e225bfcc731beb9f69092bc43f4f8768251f7ef78",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.0.mlp.down_proj.weight",
"sha256": "55a18b47140862c7fdc79d9574a847899b457423b56a2beb4a846fd96c831133",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.down_proj.scales",
"sha256": "66fee9b64196039a476ce75a19e4c1593077b503a54f30619bb8095d04d95741",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.down_proj.biases",
"sha256": "b1d9eb26b99f5cb87af3fa13c3c79f3fafb690e0d66cf2acb4d70fd61eb3f5dd",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.0.mlp.gate_proj",
"sha256": "08d2ad83a1751285f08ae4820774dd35a646993721bc1ac483e494d0311fb88e",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.0.mlp.gate_proj.weight",
"sha256": "2ac7e80dcc048185d3dbcd83fa3067cfc3a95d9377d430ab0d8ea0321cef52eb",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.gate_proj.scales",
"sha256": "243920ff3efa646b71fbc5f71be11e041bdc24c4f48e571f7b1eab90e15d5128",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.gate_proj.biases",
"sha256": "6f28108228c5984230e7a7b6a306663080e9435bc17a4e03c9c2b8a0af75dbd7",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.0.mlp.up_proj",
"sha256": "130e0183ca5510146b4321f0300a6591583e3015d5f9d75345b28ca4f54b7155",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.0.mlp.up_proj.weight",
"sha256": "0ba14733aa381d4adfba4235f583beb18e760667d8629963487775e4611f3b5d",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.up_proj.scales",
"sha256": "fd2be9976094e797367dfd5bb99960c62838fb87d9549d975cb7ad3c5065294a",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.0.mlp.up_proj.biases",
"sha256": "514d6cc49036efe05fe8898fb19311ed2fa5d23bccd2d43a5ded1f8e76a1e5af",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.1.linear_attn.in_proj_a",
"sha256": "942c3cbb0319900ce87d6bccdcb284465b237ddd8fa55f61f1fa3d3487df9166",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.1.linear_attn.in_proj_a.weight",
"sha256": "6eedba175700f61d912cdd59fbbc187b5474529dc5297b7ccc4b02e669ee6d81",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_a.scales",
"sha256": "4f3925ca05cdf17f1f038b2e00342be421fd7bafdb2c120056af4a403b9b054c",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_a.biases",
"sha256": "17641fc5d2f09ee94268adfa9cca955f304312e03bad7036eb1960cbe30e60ee",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.1.linear_attn.in_proj_b",
"sha256": "abdd60c090a9d3058c7a5ef75fb9531c7b03b338d6644b0627c2d7d9fa0f3f58",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.1.linear_attn.in_proj_b.weight",
"sha256": "d64246086613106bafea43c006e31339bf784a89b05fdd3ca16e5fdce73a295c",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_b.scales",
"sha256": "3401091bbf1973cd2db24d6c12ad9bdbd668a27a607d5cd0cdc516c991460381",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_b.biases",
"sha256": "89b7485046876ca0c17f6caefa9bd3fe4445dad0996a1e3c5f981733494f4f3c",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.1.linear_attn.in_proj_qkv",
"sha256": "4551c5d0ab90f2d124d5ce0fc73c5450c94386275086b4092bc91842a899122d",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.1.linear_attn.in_proj_qkv.weight",
"sha256": "d754916fb769c301ae711062073679e737140157a15e1e94b5dd8224cbd7bf9e",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_qkv.scales",
"sha256": "339ff39518fe5ab4a6ae9d609e956db138b7b5f668a6f1dea684d22e7d908e64",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_qkv.biases",
"sha256": "7276c2ebd4ad0cec0fd6074abb021db70339f0e252e23d67b20ff285520b5d19",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.1.linear_attn.in_proj_z",
"sha256": "96683fd290095e12f54285e094ca4686454ec95cb41e97ecaeb6b2ff44c84440",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.1.linear_attn.in_proj_z.weight",
"sha256": "cdc3ca0f8495a416c6f253657611d54bc95eeb9c2f5556b60a7de073d046b8a4",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_z.scales",
"sha256": "4921403d6f428d75005cca309629c98a6245d0c44a70e803fa411c25a2e9e118",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.in_proj_z.biases",
"sha256": "e641a00515cdfaa28f79754de8cc4efcc29a75d1a318b34c45dec0dfb042e6d4",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.1.linear_attn.out_proj",
"sha256": "3d3cdab57c6ac5d262e27e25ec7f7c8ed96b6929d2a428f6489593e955dd5e8e",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.1.linear_attn.out_proj.weight",
"sha256": "6165727ae8bff4af77dcdb907fd36cd04b8f6296454ddd0da78bb8258b7661b9",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.out_proj.scales",
"sha256": "c190e452dd2d7fde28a187ebec1eaf6ad2cd667d6a52d0b89fee62bef68c64e3",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.1.linear_attn.out_proj.biases",
"sha256": "cf8b4262c5e1d7c3265df534327c5fb258b34f35ad312c222295d66eec5ded85",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.1.mlp.down_proj",
"sha256": "85b585f03990b5cb67c2c4ffc942748db0da6a7c378f202a60340aebe8e7654a",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.1.mlp.down_proj.weight",
"sha256": "7f8c0d9ba0a20ab51b9ca97ca4c31ed35e45e1dda69941a03fe43f1bf6e79534",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.down_proj.scales",
"sha256": "6c2f64abaa739427178ec00af062ab753cd19350393ad4d562e29ff931d41e5f",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.down_proj.biases",
"sha256": "68e65484f99b62da8136eef9064f6c78c474e5a373d6c8d4b6b00f0bae27a5c2",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.1.mlp.gate_proj",
"sha256": "3f9e75d7850ccbebb1f15e676fc288f9b8e1ca37907d55aeb4c1425b2e6722af",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.1.mlp.gate_proj.weight",
"sha256": "2edf3a44cb220ccea3068204df56f292086dc772067cdf9886d9b28224533d67",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.gate_proj.scales",
"sha256": "00da2b505f0cb61c448d0dc934aa582e7f91683e4e177ea785a244a645560376",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.gate_proj.biases",
"sha256": "22ea48cf3e60a5cb3804f6d2260546b3f945149cf5c48190f372c6ba6f8e2052",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.1.mlp.up_proj",
"sha256": "a3dde85d243f813319740ff34cf77d6bcb788e29e38bc0a1e012f7347d4111f5",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.1.mlp.up_proj.weight",
"sha256": "845e121d4147a1ee9e8b5c2b109e065f17dd9d00a43698c9e79303d710dffade",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.up_proj.scales",
"sha256": "5f70b7665d7a7f9543b7a9d1106a3e10251a446098b1a3cf5e628deb6658b9ee",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.1.mlp.up_proj.biases",
"sha256": "074d1f0b6519c7223f7ed701ff9a7d8c8c6fbf5642a09106ede7b02b0349b532",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.10.linear_attn.in_proj_a",
"sha256": "8ee54ad1c9aea31a803d35762374cf4301c0f438a225f396ac6e22041fe9a808",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.10.linear_attn.in_proj_a.weight",
"sha256": "ca7d77956504068012361e3a7d791e2ac77b81c068529cfa52aa2e4fd5f396f2",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_a.scales",
"sha256": "b1366d7dd814f34984072eaaad89afe5ca1bc470ad35696eea8d8d9d5f65bcc4",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_a.biases",
"sha256": "9c9193f2c3b285439dc42203d23962d8657bd50606fce3012ee6eabfa909e5ed",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.10.linear_attn.in_proj_b",
"sha256": "78303af905a64b9d0e95f8c52f158b7896bc57606430cddc226c886c2fe20aaa",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.10.linear_attn.in_proj_b.weight",
"sha256": "d0674f003b07b3c97b0d4f4b8ac37405fa62f505ec1260c01db75ac568179f73",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_b.scales",
"sha256": "84ca52138906fefc577a62ad1515a2fd7155c05dfa90921d2b1e7f369484ddf2",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_b.biases",
"sha256": "888f1b92a3ebbad7ed85b603017f2f3147834eaf3db026b04d06d2ab039c491f",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.10.linear_attn.in_proj_qkv",
"sha256": "4b1cef8bd36fef9fb224272c4d485569547b0cb2bcbd71226fb5ea8071eb5192",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.10.linear_attn.in_proj_qkv.weight",
"sha256": "12812478786650f2da3029ab08dbe884239cc8ee69ddd38d3dd523de5ebb23e9",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_qkv.scales",
"sha256": "e846c3caef76123c37685254cf346de8769d5984425f56ab936644ab31ba37c5",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_qkv.biases",
"sha256": "42f83a78a7949ae65a8e00e3f1df98cb787de3ba78c37e4e1eeeef66cf4736e5",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.10.linear_attn.in_proj_z",
"sha256": "f0a58ce2b9a523a0b92978d6d041858a80b854e74288c644e778d37a94b403c5",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.10.linear_attn.in_proj_z.weight",
"sha256": "6f316a14ecbd95a6f763d043d957ae185992aedf4a77a10897d8ea65d3e91acd",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_z.scales",
"sha256": "47b9cda0d56a063d45209007d8ca5179036ecfbf10193e6bf5cf94e1aa8a3950",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.in_proj_z.biases",
"sha256": "e024363a98efbdd42dbe23966cd68f86367e2ff860edbdc34c3d53df9e0561c8",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.10.linear_attn.out_proj",
"sha256": "88f6d0eddddd9dd116f302f44fcd2ed9520ee35e2c84e9d9ecd24cc0d90a1940",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.10.linear_attn.out_proj.weight",
"sha256": "af227aeeb39a97964359050b5e21e55de2496e07817ca628b6f076224c192703",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.out_proj.scales",
"sha256": "ef429e71bbe3bacdbf19b1732bd115bda60646a8e2ec6fdc1fd3800d12dc9666",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.10.linear_attn.out_proj.biases",
"sha256": "1becdeebf393ea25c8822b6fe539844dd29c76cbda32e8e4b879d908b519fcfb",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.10.mlp.down_proj",
"sha256": "44114e0088d6f36bc8a2f7b4ab5c6401cb77e4efc5ae71bfdbc06fbdee644637",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.10.mlp.down_proj.weight",
"sha256": "3ab989e23810f785a92b8508ee73b6195d5aa48201db8e46e9f1ff3a7be7720a",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.down_proj.scales",
"sha256": "21cff39a88b4f989e176fc2e9e06e76312f31643f2dc145e34a27426693217c2",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.down_proj.biases",
"sha256": "5886ac3aea9d688f99e6d91089a8628e1499d923d5c822eb2b7060113eecc8df",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.10.mlp.gate_proj",
"sha256": "11f9e81952af1b2a7b166102ced990698b393abc6985e0372a357feed07e070b",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.10.mlp.gate_proj.weight",
"sha256": "6705f2fb216346369901fa108c4ff299370991274fec19e9dced52205cb4a06f",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.gate_proj.scales",
"sha256": "6b7b35d8696f078f5b9f4d8de4d1cf9bc7b3e465c4725ee4294bcc25126d2f6e",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.gate_proj.biases",
"sha256": "2f610695b323eeaebbacfc0fca91be0fba552babf9d27b53b6af9727dbce6d69",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.10.mlp.up_proj",
"sha256": "bbe0575be367c603cedbeb761a5d1f2a99afae1df9db8f2b03f4df01e753b45e",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.10.mlp.up_proj.weight",
"sha256": "7fb3636c246ffdcb78666b0f84e44a0893992d1221db8a2a5ce9a13ee522f89b",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.up_proj.scales",
"sha256": "d3ba474ea48902bc13ac91c2c43fba2916bdac0de202596e045d94444d3d3a77",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.10.mlp.up_proj.biases",
"sha256": "f0083c390ccdc05c83f8ecf617e1864b448ad6939259ddc520d812dd25de165e",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.11.mlp.down_proj",
"sha256": "bdd05d4916588a285afbf25a2b95ba03f25fdfcef518f93abe06818a1fd8c1b8",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.11.mlp.down_proj.weight",
"sha256": "0556e2d07551e267979fdb8b1d748c5ebe3d4855bf13242cf13e5055c36ddc84",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.down_proj.scales",
"sha256": "b1956b414ffa8b00d4ca369db793842493c03c36003c031ae33a57d7e3537241",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.down_proj.biases",
"sha256": "fb69e8b6d98367ea5716ae1deddb22fb6c3365b5fa32c6c0b2a464d64c58159e",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.11.mlp.gate_proj",
"sha256": "0fabdca8cc4fcb70c22de166321d4bfb90e9faf367790cfe56f691631486be64",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.11.mlp.gate_proj.weight",
"sha256": "2dbcf8c0958ea328905e87f4b3491390788b063cca0bc193ed9944891d5ea809",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.gate_proj.scales",
"sha256": "8e6af0aed5bfd389c0d6670c3c7d6d8a5e75caaa91f3e0239755bc0324072f81",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.gate_proj.biases",
"sha256": "523a96f33493e3fb837df6eb4e3052eb9d995d3e292fbf3e08b36b2969e46f37",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.11.mlp.up_proj",
"sha256": "ee4f4bb4d2368018828050400f63f52e78b70c7def2d2b56f161c7bfe99a8149",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.11.mlp.up_proj.weight",
"sha256": "63acc6176c157326ecdc67b336717653abb7542e6bd4fad9b85e771389a6c845",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.up_proj.scales",
"sha256": "4f3e095e4a9e71607c7714cc93edb4a796af007c8183be8dd64e3e4bad26ce58",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.11.mlp.up_proj.biases",
"sha256": "c55163d79eea4634fae5c4c3561178454bd4bc7251b74442654858132befa19a",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.11.self_attn.k_proj",
"sha256": "ffa78db63bdf35c91dfa602ce5e5716f7a21679eb4c1449aea652f9b549053c5",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.11.self_attn.k_proj.weight",
"sha256": "eec5261d788f02cc4d855683a3ebb8286aa3558f793b4bb3653097f445a6fcf2",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.k_proj.scales",
"sha256": "cef71adb083d1c59a280d1cb4277d12f963220420b3d910bb631f5ad9404d544",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.k_proj.biases",
"sha256": "337272c3c06166e4619c410b19e2fc20b45a5efc96f1f45c55a56ae85b752bd5",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.11.self_attn.o_proj",
"sha256": "9ee796c337fa59b4433d7471289aa424a57ff7cfcd7af0a2c9aecd723d32b7f0",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.11.self_attn.o_proj.weight",
"sha256": "21feb58a9dd3ecbb6c4da7d8e81461c7772aaba8e7ffc513e8eced6ebbf290f8",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.o_proj.scales",
"sha256": "b3da8ef4687780281fce3c41e8975465709ab69903212416990f8f8013f29249",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.o_proj.biases",
"sha256": "250f879df0eb8e043354a3d05fadef2e32dfcc26762b32c30f060fca06d82d2f",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.11.self_attn.q_proj",
"sha256": "3c97b840099f3e9e8a8a7aa3c9d14272b020896a89b5d1226f33bb80e3608bc5",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.11.self_attn.q_proj.weight",
"sha256": "697152a71701fb4d818b7e41f81efd783a44b24a082d1fe459e86e751ef23e74",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.q_proj.scales",
"sha256": "dba8abe64621d5701cef12ba918beddb0ef17d2198718644ec6c88a199c38803",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.q_proj.biases",
"sha256": "31910a752393309725a6c879d533364f8d88f3378c407aa8c8b7bc70b1e3f95a",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.11.self_attn.v_proj",
"sha256": "eefa7ec261c91e9f9eb3f4e7f5b621d0ce50e0b07584274f804c2fa403d9bf08",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.11.self_attn.v_proj.weight",
"sha256": "e7740bc22daa0d262b868c01a4dc2c14afa8b5d57eb88d3ed1f11663448730f0",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.v_proj.scales",
"sha256": "6cc169ed1e143039e9c6a85fe500c43d86dacb1ea7d63cd8c2096880ed941875",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.11.self_attn.v_proj.biases",
"sha256": "243654a20f7eeda1b9035cc3a7fa5c83ee9a2558a4546068ddcd3c32dafcf2d0",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.12.linear_attn.in_proj_a",
"sha256": "78d3daf83436644090f6e9c8e2c46a6487dce84d30a9de0e0c10f94a23df2645",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.12.linear_attn.in_proj_a.weight",
"sha256": "00c335c9469302bb583c92fc3b2747670e1b19b4210f90343ac598f3396150b9",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_a.scales",
"sha256": "cae9adad40a8af83fb1015d3d1c761797715c9c3429d281b3f1c60bebb5d41f8",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_a.biases",
"sha256": "b64b366e334f91ea5615be6bbe389bd8394abf7d534e0f18a0c98a2402608876",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.12.linear_attn.in_proj_b",
"sha256": "43aa0f624f82b3ab35c3884ee615dbf12e0abf7a11f728f98255fcf5bfe97ffc",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.12.linear_attn.in_proj_b.weight",
"sha256": "04c05acd53b1039a331c94b49318e575fabc84f5f12b62b796092c5fa4c714c2",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_b.scales",
"sha256": "bffb39c29156c3c5f34fc167e17ee233f10ce025185e164695c4abb8bb1068a5",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_b.biases",
"sha256": "1cc7c00fed99cbb83aba64c8c7bc1ed27f9befff133aeca0dab792710190b35f",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.12.linear_attn.in_proj_qkv",
"sha256": "b2ed995914b7bf938c667098fb3c84c977be59c5efb25c4aaf516459eb2707c9",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.12.linear_attn.in_proj_qkv.weight",
"sha256": "cdfdf269b312dedeb151867d7f07d8aaaad5c903c015bd65cefd02ccd909f078",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_qkv.scales",
"sha256": "11cd869d84c964fffc7566991763c52be23f4e0a12248fe393f1c24290bb05df",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_qkv.biases",
"sha256": "df675cf706d56a90a7856a57ba3e1abdb0e7ac48998267b9e7f04280e4eebe28",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.12.linear_attn.in_proj_z",
"sha256": "623f536a5e1071e8688236d5a10aa31cc45fbd4a00ae1aea015e54e4ffba3d06",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.12.linear_attn.in_proj_z.weight",
"sha256": "bc4afa0338b0ed287dc3eac26121669c04de2b81bfba1a52c597a38d6686e50d",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_z.scales",
"sha256": "e79930c9affd24f665933bbc4c651ee5db69f71fa21875bd47b9861393df14f4",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.in_proj_z.biases",
"sha256": "951aa31fcd1f1d1e5ad5adbbd8b90cf6d9b392d68445f413769556e48f10bdf8",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.12.linear_attn.out_proj",
"sha256": "f5da85b689cd5dfeb24e356a6ac04c94b38fffc7041225a38d11dd15c46aca39",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.12.linear_attn.out_proj.weight",
"sha256": "d8729ba40b613013326a4af0abd6e91e9ba09eb0bdca98b254c533aa174bd34b",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.out_proj.scales",
"sha256": "bfd3d01841ae7ae72e5416729161fee454f7b85ef2d9207037a42daa9daeb85c",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.12.linear_attn.out_proj.biases",
"sha256": "64b942b8efff77ee3ffc1471b4149e60ca39efbc5754dcaa9e36141fc6ac3fcf",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.12.mlp.down_proj",
"sha256": "5dc1c1d77971e981699799df9161ddecdbe34a9fe535ed565860248ae43e6910",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.12.mlp.down_proj.weight",
"sha256": "2f849a186f9a52d7fadcb2c791518a84e62329a840e4b779ff1882821cfcfd38",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.down_proj.scales",
"sha256": "ce6a98e0392e6ec95aefed4a427f2b5ea7231a07886fdf55035b9003c4bf3f31",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.down_proj.biases",
"sha256": "a240bdad6fb5eefb8807653076b801ca84f217fa7163747e9d47fca4a011d576",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.12.mlp.gate_proj",
"sha256": "4bc808e697840511d63801f9177de047b045bc9908afd4164cf7345566a29481",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.12.mlp.gate_proj.weight",
"sha256": "b0878d623c09a1294901df0a5b39aae8b0070f6dbbcf9bc0905c9de38b2dce20",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.gate_proj.scales",
"sha256": "4eaecd1afd36c9a178b5548154130ebe4095dfe80d6796f9f49a14cdf15568e7",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.gate_proj.biases",
"sha256": "3c936bea783ceafc5472a6e2792518213d01f8a3f9760d5e46cea7bb268b17b3",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.12.mlp.up_proj",
"sha256": "3523c767cea8ee38092c69aaa79d700f7dc245bb8d651a352a98fa8aefdeee9a",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.12.mlp.up_proj.weight",
"sha256": "b641264220f3601c3b037129da8aa7683019ae1c5139ed2c4db839ae0babe134",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.up_proj.scales",
"sha256": "d4030d9e9f122354ddcd80c0fbb4d736952e1f651b6812ef19cb95815ee354a4",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.12.mlp.up_proj.biases",
"sha256": "f7836c43b6a139d9be93259d46ada78eb0288f8fa4c725eea5df8decad3f0d09",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.13.linear_attn.in_proj_a",
"sha256": "95e2178d070ec9e3fdee3bee8dfe09f35449dd9121b01c2f9a63f05c8cdc3d09",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.13.linear_attn.in_proj_a.weight",
"sha256": "6f58e39c32d3ce24be7010fe51e8ca709ce46aa2349810b772eb03800bd27162",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_a.scales",
"sha256": "61d2c692cb033a6b0fe90e5dafada812361d191762633c157261e0cbd35cea0d",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_a.biases",
"sha256": "de20b4d921ef7d352482ba33914d5f489180319198473e699e3f45d9c6d4530f",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.13.linear_attn.in_proj_b",
"sha256": "87ec5341f537a0bea0ba6400c440a3cea2071cc0b0e79c998704a2003bfbf4a5",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.13.linear_attn.in_proj_b.weight",
"sha256": "16b514e7aaf762dff1bd18046169cd32ac7aa1a3e61cd46a04b51b16b95658ee",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_b.scales",
"sha256": "54c8b8d71fc96240eb904fde13bf77bb46465255402d47ec3d5d724a6f0550cd",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_b.biases",
"sha256": "ad52b0e3516c21f1399ab819c870d84bfd736f49afd28b4e4e566a2e150d9c9f",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.13.linear_attn.in_proj_qkv",
"sha256": "d95ab2199543b30e4e24f46382f7d73d16b4a8510199dc389459c7a627df2827",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.13.linear_attn.in_proj_qkv.weight",
"sha256": "bc2a9d21c00a25f2b43fa22744ecc2409f19fa9d7a34c24a4c1b75f87fdee897",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_qkv.scales",
"sha256": "8dadeda820ade5fc361d0db57f272a2813c784405389ffd309f631bcc569a53d",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_qkv.biases",
"sha256": "b6ebcfad4225c8d9b4cec990ff2642830322a13193cd5e0422f4730251a85272",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.13.linear_attn.in_proj_z",
"sha256": "e2649ecde5d29875029586c4fe32a21126277db418465800797df058bc93652a",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.13.linear_attn.in_proj_z.weight",
"sha256": "1571cdc926bbdeb65282a137ee011ddbf220eb2f052bf48b30bacb2834b6def2",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_z.scales",
"sha256": "989048d1683c5efcca60bf2b942459b9e6e13ff2359b8d17483c114bf92f343a",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.in_proj_z.biases",
"sha256": "81a6f9c2e787ed51d8ca5f1d9a362743c6ba771cc065ed614f43e6d44cb3681b",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.13.linear_attn.out_proj",
"sha256": "1b797a28b12e98274cebe5b8a6c6c10f62adc32956150980f6716bebfaec9681",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.13.linear_attn.out_proj.weight",
"sha256": "79f48e17e1f94283f30ed3afaaa2d2f5cec2f4aa1db112f689ade72d936a786a",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.out_proj.scales",
"sha256": "2c05347b6dbff02cdedd3c558ab05b71f40081a82b40152a02bec139648b2900",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.13.linear_attn.out_proj.biases",
"sha256": "ea66149221970e8b2ff19bea36523f596727edb4ec3db40c341bc3feaaae4f79",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.13.mlp.down_proj",
"sha256": "4eb64764342bf532d987a4ab0becf44d9d5ebd2c03c51628e28e37e8f37e200d",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.13.mlp.down_proj.weight",
"sha256": "4d7b33a591c970dae1f1e9a13ed6b0132c530187d830483afb09aa728f2aab42",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.down_proj.scales",
"sha256": "2c2249e6dca2a4955f0e613a5010c41478a71bbfa329373eb7076edaa937afca",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.down_proj.biases",
"sha256": "af40b47b3edecda178063302b662f34ff4ed0b32c660fbd85f0c4db78560a954",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.13.mlp.gate_proj",
"sha256": "bdb842d31ad4565fd3c78ac510b0abbb7c372470db94b49027aa24d4a9c1ce11",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.13.mlp.gate_proj.weight",
"sha256": "a81aef22307cf7259496d1b4cde570338734cf588fbad46c4f9f1819d6695371",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.gate_proj.scales",
"sha256": "3132ff6c486b9f1d01d6e274c942f3e722a5f73124ff765235df41966e4d1fda",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.gate_proj.biases",
"sha256": "445042feb441d4ab2e456dee8d947568dec657d126ca3d2caee7dfc69b167c98",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.13.mlp.up_proj",
"sha256": "0f688f57bc13855bf8d7958ce63dcddef5c51a21957546cd80cdc36634183057",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.13.mlp.up_proj.weight",
"sha256": "64d6ddd7c96593feb5246217040f4904de2134a7f44f0ca34372354e3fada84a",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.up_proj.scales",
"sha256": "d70a699e17ae9981b32ce7686d0ff95dbe969d0d0817e40130ca1a15c18b88f7",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.13.mlp.up_proj.biases",
"sha256": "976d5d4a7f9132096d341ef8bb0aa34f37a5aea0fa1b52e0b73b3d3404d0ba42",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.14.linear_attn.in_proj_a",
"sha256": "aac82a7e9192681599f2ea6a8222cc079152906d7f9fde74f3e98911a83f78ff",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.14.linear_attn.in_proj_a.weight",
"sha256": "3a8cc1c4d692dc5b0e58f2aecfbc79ac4d9845d74ea641d867772f1a75a2a441",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_a.scales",
"sha256": "d7c9cf9da67be1a410b53d931782ec940855b019eb6352507b2eb56ee6172b84",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_a.biases",
"sha256": "d7b292acc8119db8d0dc72972e60ed54e4805388f67921fdeee2a9f99d678306",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.14.linear_attn.in_proj_b",
"sha256": "c7eef7c1d3277c584b27d46bdea4f6e1e8ae6a84add4db019d256b71c9cd5b29",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.14.linear_attn.in_proj_b.weight",
"sha256": "a5c2418a973e0f30aa1fc3b85f134c607904a7fae60a40639520e8b43d4381a4",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_b.scales",
"sha256": "df1f40f41d1bce9035d7222cb661a0f7b7b072de486426719d35d8ac10272045",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_b.biases",
"sha256": "47b3dac6bd78eaf9b03441807297655f5b7b2a71d70de45af0c62d8de8d5501a",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.14.linear_attn.in_proj_qkv",
"sha256": "149cda991dd8c738ceb2b32af489a9ff5fd848a4c3f0c3c80097a4e40327e64f",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.14.linear_attn.in_proj_qkv.weight",
"sha256": "0b8237cacfc68600bd6dd9e33b087e10a354d626abacce667c04672910e534dc",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_qkv.scales",
"sha256": "97b726b7030495a02cd8f6a185a4cd8638d13c2df4abe0a2289dc97f548734a6",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_qkv.biases",
"sha256": "d6f5699eb441ba34481eb1a52656a78b3d15d90fe9d104dd4986ec1328ba44bf",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.14.linear_attn.in_proj_z",
"sha256": "3ea375d722b880c53a661bb8f270021f5b3b97552513891b6d25ace5ce03cb27",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.14.linear_attn.in_proj_z.weight",
"sha256": "1db500a7a90296f6ecf261d7dfd70212027c0b042ea5ab2682c4fc97da88522f",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_z.scales",
"sha256": "dcf39daf6b12c73905e90d84659166c984a32235f7049e04a435e3a878ccf423",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.in_proj_z.biases",
"sha256": "2797991f50eaf9a66ee00a96c23e262c9c45b53ebf8eeaa5648e78c711c2ce15",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.14.linear_attn.out_proj",
"sha256": "09b21fbc71cb7c158fbcc56de8c5c6999321801f3639db93b1c34028f1f78b03",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.14.linear_attn.out_proj.weight",
"sha256": "fe80617939863c925eb3c8f30573a2d7cd23c924ab84cee4299ffeda99af3bcf",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.out_proj.scales",
"sha256": "8c4e126d2ff91f6e22f460b40bd3cae271c79f653c746a8136969f05f84208d6",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.14.linear_attn.out_proj.biases",
"sha256": "5caa9d4a5dd4a6ccba07d0b6ea029f134992cdf9ba1da71649a051da4d191206",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.14.mlp.down_proj",
"sha256": "789134e1049029410d2efed335cf2d327e277652652dde8d074caf2ffa750e3e",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.14.mlp.down_proj.weight",
"sha256": "d33fb4ba6ca68d0190fae08d6e186c3096c4abdd67e817c6e9a0e05db4629da3",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.down_proj.scales",
"sha256": "17ad2428b064b6862d6a56552634913fe17fc7969f786faa9eb8ce1259efbe40",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.down_proj.biases",
"sha256": "ec04e6189a39460cf7af9e950263d10626411c893683f2a6bfcd42c8114b57e5",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.14.mlp.gate_proj",
"sha256": "320fdca7214ba0c696b4e44b90e96279d609e2598019a62c3eac9e34063320b1",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.14.mlp.gate_proj.weight",
"sha256": "24a453db88c363dc8652ba6f2c8a1172f0231885a7b9aa072cc0aed7341d5336",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.gate_proj.scales",
"sha256": "a79e020fd770e855b4af65f084cb772b54069df57c945a3fba81fa8ec3313bfd",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.gate_proj.biases",
"sha256": "34d9f6c3541824c0b9511d100643a9d5e9c50045c5b3ca6cafccc51644250e64",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.14.mlp.up_proj",
"sha256": "7942d41f357e03df568fbfc4faef17d073524146f680c3649f88448bfd243a21",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.14.mlp.up_proj.weight",
"sha256": "aa28e89d86e1abafb720469604d7611799c17201e2193c2e71c8fce048c62957",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.up_proj.scales",
"sha256": "9f12fdf1a12cf709a1491c4be461f683b567e1362917db159615bfbf8505c780",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.14.mlp.up_proj.biases",
"sha256": "67bba353de392e8ff0be6c418febd7ccc087fcffecfe8bd3ebe3ab100afd0d35",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.15.mlp.down_proj",
"sha256": "58b3e255eb3ae37b68e6b8760350e3643169b8f37d6f1832f3e07feff9ec9e00",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.15.mlp.down_proj.weight",
"sha256": "7eb9e09621984238b52198d55364c31eb150a8c950aa81307f700c39789541ab",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.down_proj.scales",
"sha256": "44c82f794cd6169c71139e368f4d6d4f205d018936ccc43c24e4360bfa7d8671",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.down_proj.biases",
"sha256": "c288ad7a9e8087e04f3a9844bb0d454f61dd352d3513d121819ae84000c4c043",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.15.mlp.gate_proj",
"sha256": "068f3c30e7bb0e59801e3b4827a262958e058c9f981b2a619e00db5e96cd13ba",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.15.mlp.gate_proj.weight",
"sha256": "1919d7e8e9d06d83d30e97ba8c89ac8fc0c216dfe05fbf69d7c0b925ead28b07",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.gate_proj.scales",
"sha256": "98a132032d3b5a60e288f1ec40bfd411bc5f411a007782bfaf8780433257a09f",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.gate_proj.biases",
"sha256": "959d3de30adac20ca85ce8a16781a535dc977b26905754ef7c2171d122e373a8",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.15.mlp.up_proj",
"sha256": "95d3a73f0935844f37fdfdd97f7ad439bda63be4a0582373c54f00a96b7a0ecb",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.15.mlp.up_proj.weight",
"sha256": "7066fe99fb1834232806e83e7c9463912d536295751adfba7d239262c13c1057",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.up_proj.scales",
"sha256": "82ec187ecf966f64a8920304dc2178a33836b17a612affbe891a76ecd9d34b93",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.15.mlp.up_proj.biases",
"sha256": "3c5d5a6d1173df53ca5bd0cf30bacebd6a942a1788e2c9e3bb752e6371f696fb",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.15.self_attn.k_proj",
"sha256": "2d441ab74688db1882bf309d611daa77e2fd794e5393938baeeea4e863645e94",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.15.self_attn.k_proj.weight",
"sha256": "4dda5082ca8cc7672b537f1bf957983cde56da19625dd1b092b376f182aecc6d",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.k_proj.scales",
"sha256": "0c4eb66688cda4c1f90a9ec74af24ed2dbda6842aba05338187187936e50d3a1",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.k_proj.biases",
"sha256": "6e4e07aaac3ea4c5a26c97d4b2a107a1c5782d39f8ff3db5d12ce6ec57713df3",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.15.self_attn.o_proj",
"sha256": "d9901b524cc0357fdb96ba4ffa7368be9fa1980cfa5e2c29e707be1e74dcf935",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.15.self_attn.o_proj.weight",
"sha256": "15952aa388388eb8ed80ce727c90ac734140128fc89257fbaab3a811ac9c2653",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.o_proj.scales",
"sha256": "6c12ce275c3e1920387a8f4f3ca36d8008d8b92e07f02718788b1bfada3d6fd6",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.o_proj.biases",
"sha256": "5f52aae19b5627447cda24634caf4aa764f9209c686234d65f4b9e017bd220ca",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.15.self_attn.q_proj",
"sha256": "e201eb19c237f8bbb0d76d4e994fe66520d33263f9e990da2a95524d5387e071",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.15.self_attn.q_proj.weight",
"sha256": "9e2f2a043c1555de153e7c487804e7036d15356238c31e9c2affd1a39a12cde7",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.q_proj.scales",
"sha256": "fd1221d81bcf5109d4f6cf9b319bae072085a73e07c52d64da31a2a672ae549f",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.q_proj.biases",
"sha256": "37ccb414b7547d82bff7de85a910e6fbade8139b1dc3ff8c99eadc698fed9068",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.15.self_attn.v_proj",
"sha256": "44db831f609cb882c9146ea42a94a8bd93b27fd662c4dd663335fa8d6f566658",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.15.self_attn.v_proj.weight",
"sha256": "557ebc70420a94e13cba34719a70e435a33f542718a2d77039ead0cb98b6475a",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.v_proj.scales",
"sha256": "1a53cc5a0b3d671dd282732dd6f7fbe25f5a2b78eceeed1eb7e9d359d4212769",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.15.self_attn.v_proj.biases",
"sha256": "db1046d995dd6de7091877f151b170c291cbcaf9bc805deacc30bbfd7c418942",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.16.linear_attn.in_proj_a",
"sha256": "5c20edab4d727e20785b10b8b658fdc3ca8b15ecde0b9cbc4ee7eb726e4bd9a1",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.16.linear_attn.in_proj_a.weight",
"sha256": "e7ee4a3e4ccace4100a82b8260a13f9878f43e3799dc89bdc1ea0659cf39ed07",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_a.scales",
"sha256": "e6033e95d3b65e815ff5dc765907e6a189e75a1cd34fca4516c480dda11a570b",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_a.biases",
"sha256": "b5582abf0cd834afe6afe6be871a338b0eabaccf7453dce9eeb691fa756b8ad4",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.16.linear_attn.in_proj_b",
"sha256": "6dc40e43ba80180267d93be17a3407649b9de82031f38bb458274a18dae1c42c",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.16.linear_attn.in_proj_b.weight",
"sha256": "38c4f15c41d8d47aa058c0dcedb3ea7696508d06d8e4a207d5ee93c7627b2d7c",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_b.scales",
"sha256": "3a540b403c18d3362d586fcdb1885d9b180b99a9700a5024837d5eeef00d4422",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_b.biases",
"sha256": "238af9c37c49b907c49537acb36ea167a491c2a6c729288da55656e22f5b2813",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.16.linear_attn.in_proj_qkv",
"sha256": "ea70218fc0d41fa92766ba3bfe0f4e00bdfa0f5d2838b131c153e218fd33e6e1",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.16.linear_attn.in_proj_qkv.weight",
"sha256": "794ee0f0cde7107a8393fbd20ea282f5bd7ea4b95beaef51be22bd969c4d44a9",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_qkv.scales",
"sha256": "4facb051ab2ae2fb0c410cfa2f7047a1786b53aefdfc76218ede72c63d2c1f6d",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_qkv.biases",
"sha256": "b18905f8fa1f9c7433dd7215806cd50cd0ca0629715d447e8aee0ac1909f35c1",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.16.linear_attn.in_proj_z",
"sha256": "4df444693e786afb4271077164bb7c85abfe487aa4a2cad5d4048bfc94e167b6",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.16.linear_attn.in_proj_z.weight",
"sha256": "37b758074e6e95cc6e5672af808da1eeda11d121ff14259e317387999a5f95ed",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_z.scales",
"sha256": "9a714165708519fe893688c5374c9cc002978db6340deadd494b8a2bb0259f44",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.in_proj_z.biases",
"sha256": "1eec060a1ea5cbb8e299438220e827438c4deb55b7b5a20ac7c3e682ddd49bd3",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.16.linear_attn.out_proj",
"sha256": "c51f9688707c49704b178e75186151b98a4ae2b26328a7a7e3ee7f61467f531d",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.16.linear_attn.out_proj.weight",
"sha256": "ad324b9b2847a06466465feb1635c890b1bda3d93acf562b3aee186352e74f0e",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.out_proj.scales",
"sha256": "8ddf912ec026772f22fb2021a1716d1e6cf97b9237339a2e816ef1aa5507a531",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.16.linear_attn.out_proj.biases",
"sha256": "b051da339ef21b31884fdc37ab4ca3905c4a6735dc7dadb77fea7b82005e5ca2",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.16.mlp.down_proj",
"sha256": "b441b5f950d5c7cf5f35fd9d37e0ee69088fd0fd81d034f1ff3441cfed418515",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.16.mlp.down_proj.weight",
"sha256": "4fa25f5178dbfdbd3f727be7ab71213136bfed53ee0974451989874ced1d7063",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.down_proj.scales",
"sha256": "868f15f3b54ac417d28bd512443b443cd685fba36755b54d9cfbde9caef50f38",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.down_proj.biases",
"sha256": "31ffb9faa189b1de37e5cdb2696782607be42163de34c4cc333f6b3abb734e1e",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.16.mlp.gate_proj",
"sha256": "4b2496be6ed7f63dde268425ac8343d4805bfc9b3e774a562b8ae5b80c6b9110",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.16.mlp.gate_proj.weight",
"sha256": "6eea35763de79f1c112250af0bd02cfa777e53bf83ce1ee5d65c45b794a34aca",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.gate_proj.scales",
"sha256": "91d1198acc4160f241b1e21116d48d4bd3f285c690efb3cf027d5bb9e71292a5",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.gate_proj.biases",
"sha256": "2f03f3978c9ad87100ff29fe8c9030c683c59b17d90025983af33df20109aa83",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.16.mlp.up_proj",
"sha256": "6f697dfe9308efa32afceeb05eba34a71d021775c21adca89fc3272b149c0570",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.16.mlp.up_proj.weight",
"sha256": "23e2ba6b281338a6c76c23464e211e0c7b97b701d492f5328e1279d121d13a39",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.up_proj.scales",
"sha256": "e6b099dd3de45c9114758ac561e54d1a7b278b1f3f789774559be45c46383f68",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.16.mlp.up_proj.biases",
"sha256": "156d95ae6c4aeb033907ca953c055c2967357aea124409b903b1db6bca314e6a",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.17.linear_attn.in_proj_a",
"sha256": "1b686a8140c02e179bc29f0a47fb850cb7e5b0b8aa6eb517c3ae2e4713b4e11a",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.17.linear_attn.in_proj_a.weight",
"sha256": "b076876ae2cc76a54c206643d2832a5617f49a23c663c54484896e6d42a9bb09",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_a.scales",
"sha256": "848e9a3f40480718ae6150785b20d13cc8df21ef1524400dee0c0c7a5cd0b1e3",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_a.biases",
"sha256": "272df5274f2c79fa1ee6a4f027e453bb88116759bc80170fb0e42d442beb8992",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.17.linear_attn.in_proj_b",
"sha256": "98d8347e2e5111a49451d82559f551d7119dd2035c6f20b0cbbe469c2b1afcf4",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.17.linear_attn.in_proj_b.weight",
"sha256": "8d81803bd284ea37194dc4a4050ebe856bea3a27bf55c7ea9979df72358a45ab",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_b.scales",
"sha256": "668a327c8e6150da285d61dcd6408ec28ea8b41982469c246864db1b50d7c12b",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_b.biases",
"sha256": "079ba9588d46c8014a402c1d3aaf5a4f348449af45165c426dd6ccd31a9daef7",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.17.linear_attn.in_proj_qkv",
"sha256": "6eeba703d2958248499dc42f6ba1446283b1673ad71004b09d91542b911ba6e3",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.17.linear_attn.in_proj_qkv.weight",
"sha256": "3a2938c5559e0ff9e4c6218e57ac1909456fe39613c555c9584cf934c0c8fed4",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_qkv.scales",
"sha256": "a4fdd81aec51a47dc089ace058a208385ac766120d9ea6502908ea86ab6d7454",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_qkv.biases",
"sha256": "653d2d62572b9a7856bca9c5ebef73569bc6ba46e36c5fd5e68f05bfb937aa96",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.17.linear_attn.in_proj_z",
"sha256": "877b05a2635bcfff5f532ebb92a41d7e85f7c7a83ebace6a4e13f48388586d2f",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.17.linear_attn.in_proj_z.weight",
"sha256": "67682d766e50cc87c19bf035513473fc2dabebad973ba25e40130d4e8dcebe0e",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_z.scales",
"sha256": "be4e88aa7c058140f74cefaafad459df69c64746095d48e608a1d06b69c14a19",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.in_proj_z.biases",
"sha256": "a40325d9991198e1b41eda103f50dcf7e6d66b704b455ed9a77a82ab090dbf56",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.17.linear_attn.out_proj",
"sha256": "f1ab54a43ac14fa969908ca129d6faf73960f2b0d73c755620a42bb305878fd1",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.17.linear_attn.out_proj.weight",
"sha256": "5c31a80e8b12b5e34facab53dad494272b3437be390a925ebf3e4e559e5c471c",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.out_proj.scales",
"sha256": "835b16b454a9e18147713813773ccb8c99a254535db54e389509d3d8bf98cc64",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.17.linear_attn.out_proj.biases",
"sha256": "68175579e1bf19082a0807fbc9fce44cbf2245c8ba470e1f540b3712d6bdac53",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.17.mlp.down_proj",
"sha256": "d45e4c845e30afef1f6402c90ccf24b42109b2a3f00c5c0ec55c47e06298b079",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.17.mlp.down_proj.weight",
"sha256": "040a225f15317db4457180ba852b8abbfc875f4626e5af7302f842524cb53bc5",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.down_proj.scales",
"sha256": "f516adacf0ff619f922ec700b106ebd485fa5bbb58f2b965ca2e384b71123a23",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.down_proj.biases",
"sha256": "9c4cb552c1fd825540cf1fd72c0a16f3cfdb7e437e2b90c80e2bbaccff10834b",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.17.mlp.gate_proj",
"sha256": "b27e35e5447612e131181f162a1e0d94e25b6d772e7e1034dcb4dfc02b02d78c",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.17.mlp.gate_proj.weight",
"sha256": "05179658300c255fe108d196a1e4b98edb8ce1fbedd34139bfd3b03bafe85f51",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.gate_proj.scales",
"sha256": "ab761bcd62ec6a4d16313ee33d22eb43a2a379b22795c2eb80afa64bd3b07026",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.gate_proj.biases",
"sha256": "5d00fbf097a5e19d1341e797bdc5919b3a31fad288cd96c0d5a19144dc04fbf8",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.17.mlp.up_proj",
"sha256": "7fe50a36b359d83d466c31ba80ae643e5a2d7e061373d1a95636727f978f49da",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.17.mlp.up_proj.weight",
"sha256": "c80b0856c1cb66a4207600f3fab7e994c686781fc0b36dc193ab67112abb186a",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.up_proj.scales",
"sha256": "e2ff6cc7a80d11ede4fc61729045b9e7b8fab41bb6a3802b7eca2fc567b80a83",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.17.mlp.up_proj.biases",
"sha256": "4120ac907f8354e8bbbe2bd7db37475210f9ecaea6e778ead5493b4401368883",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.18.linear_attn.in_proj_a",
"sha256": "01dc221420bbc57ff719e3ee48e73a56a8a78350273558c1365a5b50f5bb79f7",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.18.linear_attn.in_proj_a.weight",
"sha256": "8578fc940db7e613b078b81387de29b7517e2b9f51aa15e4c8c2a37350ba7020",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_a.scales",
"sha256": "ecb407b4586284c625ff5a67f15dff1909a3c07f59019528d89dbb70c6f9310a",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_a.biases",
"sha256": "43e9986fa59f2c924e2f7ac97ffed0b462c69c51e2bd56841c0361c315896ca8",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.18.linear_attn.in_proj_b",
"sha256": "f4136d38d262416c25152e0a9e6231e4d7bf48294c4f5242ca961d1355368361",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.18.linear_attn.in_proj_b.weight",
"sha256": "c3b84fe343f113da68d4936742548fdc488608a6d504662ebdccac710a354815",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_b.scales",
"sha256": "e23ea65a125342367706d166506e4df71ae06135a43aeb0b11e12f4efddef228",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_b.biases",
"sha256": "de90b35aa812111f933ebf705227e340d9a58a393436d613cad46f5579b066e3",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.18.linear_attn.in_proj_qkv",
"sha256": "dd7d06708f8c51e2cb99c5752cf9955f7e79066b1d15cf16f32f55242b77987d",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.18.linear_attn.in_proj_qkv.weight",
"sha256": "1db89d2c206e0f36b61dad6ee953b5b0efca676fa881fd8d4e26ef3cee509ef1",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_qkv.scales",
"sha256": "aed26aa0703ea925c3ab3dc0fe3efc033a685af528fc6ea769e2ca9c6f96e15c",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_qkv.biases",
"sha256": "87d0da7dff4b02f13f0bcaa9f94af6ab8b6000140934e760911eecf939387e59",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.18.linear_attn.in_proj_z",
"sha256": "6ecbd1a627e49e444db3e2d2686dfe451217c6dc7f0223f9227eeeaa2803cf85",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.18.linear_attn.in_proj_z.weight",
"sha256": "8b7391978486fa830429216f7bf4ddef8e15e626afb2837c0ff6a21e8f0882d4",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_z.scales",
"sha256": "16e0e789a7a75b2b289e2f9202bb2a696efec1670e3eb1d44ade2c70a7dd82c2",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.in_proj_z.biases",
"sha256": "605d4a7c61509998949da0f5a28f37b944a825defe30c3e879637e77506d0053",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.18.linear_attn.out_proj",
"sha256": "b7a3186107b1b14e416f56dbb71a361c1363772525e78f74da24967b4804f5d8",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.18.linear_attn.out_proj.weight",
"sha256": "77f13b74f1203d1bc8886fa8b3e6046dc7f027bc5d57fe2d71d05de18995ec09",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.out_proj.scales",
"sha256": "a53a098be87c07eb05fec1c0b97c5607127fd2da916c1fb118aa4ec760b2009c",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.18.linear_attn.out_proj.biases",
"sha256": "89eb7854d923ff583362ffddda90fdc0733d8147707560c05f8e2290ad490ec4",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.18.mlp.down_proj",
"sha256": "1d581d9691ad1d43ed4ccd6589c37fd0fe858c27021bf46fd2ef77556c9048ff",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.18.mlp.down_proj.weight",
"sha256": "2bc198a170c4793602d34fc45a79fcb2230c33cd5b5f84039b919a119a6c40ba",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.down_proj.scales",
"sha256": "57c7bc562f13cf24be3cf05418f6e8976a7eef77b7f21622ccf0b871f73fb0d8",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.down_proj.biases",
"sha256": "da1248e1cdbd4e5d6bc3065c50a9f388f772becd396468c0402ea6a2d9c100b3",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.18.mlp.gate_proj",
"sha256": "a45829bf228ad0bff3b5c38d9b091d92fe06a199dca688f8bb5269d3e8732337",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.18.mlp.gate_proj.weight",
"sha256": "1070bcd05a7cf338f949acc62e3533d67e4e280001d98b04ba50a91bc7614612",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.gate_proj.scales",
"sha256": "dee96e33aab4200475340e361f12b6a906e6126e8c666d6cdad41caaf6d15f91",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.gate_proj.biases",
"sha256": "926e19efc11696cecf9cc26055e1e5499db9ce7954199460d514c92a32a3bbbc",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.18.mlp.up_proj",
"sha256": "6014a42fbca803a583cf6a843088ce7c10f8d99b2945acad282cb7d250769697",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.18.mlp.up_proj.weight",
"sha256": "71502847b9d4edbe60632628dd6a7f1a9e68a04995a3d0deed97815d927faea0",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.up_proj.scales",
"sha256": "8815969cfddf8d72534c27037bf06b5b66187f612b6068c610f44b929354e25b",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.18.mlp.up_proj.biases",
"sha256": "32dcf671ac17c6c39c06e6c547fafecf76b71b19a9577dbf7c25dbe82e23446f",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.19.mlp.down_proj",
"sha256": "36a34ea5969c1d0a56f49ba0e5ea75e748ffbc7069983e018c4c5091db457fc7",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.19.mlp.down_proj.weight",
"sha256": "4c2263e263dc3eac3697838934cfa9a68cf93d8e65c18e3f674bc9d69c1a7e66",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.down_proj.scales",
"sha256": "cac5a466a4ab516c53a7e5e8e22a105e5fbdfb6af7723457759b14f5fecffbe7",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.down_proj.biases",
"sha256": "adbf0c1b3ba4dd3890cfc63178483882a8e9cee36c109df96527ef41766423db",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.19.mlp.gate_proj",
"sha256": "94997b124a2ace22d3ba048a6d6f4db2d6cfeb8e0066c58d347035655999ce9b",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.19.mlp.gate_proj.weight",
"sha256": "91d9516ab07759c9b37c1717eb3f23f9ce671bb8f2581ba1dffc62659106253d",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.gate_proj.scales",
"sha256": "804f7fba3283d7b0c4be244d718c1d41a0c5aebf69b16132c8789ad1c0aa775b",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.gate_proj.biases",
"sha256": "5c59deb9e323da696f99350089420cecd7416331e9aca029171d6539e8b08274",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.19.mlp.up_proj",
"sha256": "09a8e8c9377c6d7fb1520658c48d39432f8038f6939e4225d204157eefa7ffce",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.19.mlp.up_proj.weight",
"sha256": "1b8c18d756eb1f96b4d732893b5b9652b1a5fd6088fa6711a5341d73046998aa",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.up_proj.scales",
"sha256": "a9da13cd1654d39e3472f7fa816a5642141f1d69961722e0cb983f990b3ecd6f",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.19.mlp.up_proj.biases",
"sha256": "be60cdacfa1f9e96dcf5432c5439d888998ccb18f02485dcf7c283ba96d98e11",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.19.self_attn.k_proj",
"sha256": "fe17215db0889bff88101b5b57713f60c02e0ba382a6f475dff5a9074b0fd9b4",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.19.self_attn.k_proj.weight",
"sha256": "70afc64e8af8cc2b36061e22a6e4998cf8fecaa61385d42583dc2eda800ffd1a",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.k_proj.scales",
"sha256": "bdd82631098a1c90471a20ef8907e834888d98466acc109cd59ffac48b8e43c5",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.k_proj.biases",
"sha256": "47f0d524d09c4d2d8620276acc73ae703709b1ff21e273cb311e3b51d320fa3d",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.19.self_attn.o_proj",
"sha256": "0d9fc7c9767a51b358327d2024cb811795a84b9d682acbfc757028aec9f8d86f",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.19.self_attn.o_proj.weight",
"sha256": "832cd9f198dfd9cf59e4e3a69646032a8f2e3b3772b7d4dbf1dc49b2bc87625e",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.o_proj.scales",
"sha256": "c69977839b5506864dece7ff02cb5945ad4eb61ee2f2c2e8b4e6d7e97f0d4115",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.o_proj.biases",
"sha256": "c2f41816d7e1da52e2bc5ad08ac684a7a500aaa190104aee03c73653ad51c924",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.19.self_attn.q_proj",
"sha256": "f4d2795a2c2d702837ff4b18fb19401ccef1d166fc04a9a44b9adb3bee468b6c",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.19.self_attn.q_proj.weight",
"sha256": "ba177bda0d376f72cf754adc5ee8a3285cb8a1b875ac8a59e51f3a91ac1f8e32",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.q_proj.scales",
"sha256": "ef8a281d5d7d736c72cbe7d64fd00162b2f6b592efb4d7835367746f3ac9f0ba",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.q_proj.biases",
"sha256": "f8a0cbb48a040e3635286f238f796bddc3d85d94d71c3aacb215016069ccec51",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.19.self_attn.v_proj",
"sha256": "09760c2cb92618914caa2baeaf1b9f0d2f03f10efb2205b77d06c2d1db83c4dc",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.19.self_attn.v_proj.weight",
"sha256": "084cd58aa6747472eac7771e4d5a47c24fd40c136b509dcafc6467eba85bdb73",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.v_proj.scales",
"sha256": "278551136f70b22a7b83c4f3a86c369ee394c0079a734aa83b8cf494abab32a8",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.19.self_attn.v_proj.biases",
"sha256": "d624ce0cb1997826d9332dae038a56fa4a33113ffe9cc723fbe08b49b0c54a52",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.2.linear_attn.in_proj_a",
"sha256": "36318c3d409aba910b634f2e3552af9e0b5ba2b8b64a05f58e02c18314907e06",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.2.linear_attn.in_proj_a.weight",
"sha256": "0040b5d3cc340e015f246f53bfdaf97a3c712ff086e497d8a830d23c880a2e12",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_a.scales",
"sha256": "b7809134174087769d6f8cb41e5d8192315b90945347583f2c280620a290012a",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_a.biases",
"sha256": "fb4a704234f8e031fe25c9a635238babc3c2ded1e72973daa808ec0a68c28b02",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.2.linear_attn.in_proj_b",
"sha256": "c65b17199c9b282215495788c5acceb6216500d5dcabeb6638a366d4584e8a14",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.2.linear_attn.in_proj_b.weight",
"sha256": "a577701fc25a0cf3afe7d99dc9efee3afcb0ae5ab6f248da46e0a7f0f4fd113b",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_b.scales",
"sha256": "2d50476feaa66629f06169ede24f8266646789a7734e9b297c56ecf1119ed11f",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_b.biases",
"sha256": "a31cdca0fb30db8d5454e6790ffd22c62d2e36bb547878f7c26462ecb986984b",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.2.linear_attn.in_proj_qkv",
"sha256": "d5df96d3dd44a3bd3dce2a056cc4ced77bb1f11034866e3eb67b1f59f6f6e600",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.2.linear_attn.in_proj_qkv.weight",
"sha256": "fffc8aab91cec851ca3c26b1ad579f7f7291808742790348f64b4f08c2fbe183",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_qkv.scales",
"sha256": "febc0910edc6044a66ed30f17d13e44eef142d2ac0e8bac345c0c65d169b0862",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_qkv.biases",
"sha256": "7c5570739c09f24c236972301db07280c5349afe97c8d0d487ff01c8b9406d1d",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.2.linear_attn.in_proj_z",
"sha256": "67edeea7b281393c24962d76f4608133dacbdf4b39857133d635e575b2a39941",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.2.linear_attn.in_proj_z.weight",
"sha256": "56d87dfc1b65ceff7476bf5167fd772b0ca9bf6f2222ffe7d281a8f8c671e380",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_z.scales",
"sha256": "2e827fd38f12b957bef6deac761b8fd9c1eeb8c5b2490a09589237e7abc5bb33",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.in_proj_z.biases",
"sha256": "6e19bf43a52e6a557b9dca1d76976940c5bde940fdcfa13fc32601dedcc4771b",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.2.linear_attn.out_proj",
"sha256": "aac7ec366b75bc4457bde8bc48c60d2f608d92676aff6d37193a8ce159dafe53",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.2.linear_attn.out_proj.weight",
"sha256": "2070e0464d056fbff0872cb8a29031a1167eb870666a8dde83c0cacb713485b3",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.out_proj.scales",
"sha256": "e590c53bbb1a3e3ea17e5f99f4daf1350fef7e8efbb9d01cc808082caba09550",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.2.linear_attn.out_proj.biases",
"sha256": "08ee2ad36bacb05dd6056f607952e1383a8bb5466cfb23215124287bf9faeab1",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.2.mlp.down_proj",
"sha256": "9c09097f9f7aadf094bde423c9b6870558d0d1d95c8a962b1324fb13028b6d6c",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.2.mlp.down_proj.weight",
"sha256": "276acae2384e70091e452d9e7c3678b80a4e9c86c8563615536957841912b5d0",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.down_proj.scales",
"sha256": "a1dc9a5c6de6bdc828bd46a98e05a17b2e4538de25ae1be2c4d18ace469d86b6",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.down_proj.biases",
"sha256": "5289ebad321e42de4183be78defb510448bdb2eb38ec33c72e7234940cb6d222",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.2.mlp.gate_proj",
"sha256": "d72e65bb62f099cbfcf08bebcbee614b69c59df2091f26b6b63b50db0fd68212",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.2.mlp.gate_proj.weight",
"sha256": "4d00d0734ff31b5133696061c4ccab2348fd69f15ee5e5790e8c4b7818cd210c",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.gate_proj.scales",
"sha256": "422750c23ebd389da95617a165da7f815ee766fdbbd049d4e9890a682014bbc3",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.gate_proj.biases",
"sha256": "c710f6805641af2fa4daa3fc32f14c827fd5cee28d361193d022e57cc3702cde",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.2.mlp.up_proj",
"sha256": "2ef4e69f9b3ea3e8dd64eb64e10536d9211d5ba5a912fd78781e14e74b76e1ea",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.2.mlp.up_proj.weight",
"sha256": "8438c3e9ec55e498afbb8474ec6850cb5eecf77adcedf73cb75f2e6ca7cf5407",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.up_proj.scales",
"sha256": "5731a36c497e42fb6f3fbf479ffc7862aac824fbad7019ad0d79a04e7ca13e20",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.2.mlp.up_proj.biases",
"sha256": "38ae79d3d715fd536fae2772f2d273f1f00880dc8ea20769891a400fa697b008",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.20.linear_attn.in_proj_a",
"sha256": "993e0af9ad0cb3719ff0e2e13ce7a367224f6070e44cbda149a09b50a182c905",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.20.linear_attn.in_proj_a.weight",
"sha256": "98ee0c6194c7e58273d48e9d0300bb608c156b8c255693605b4d929a5a284d34",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_a.scales",
"sha256": "251621bae202e3bdf8b140fd892d72f13373c8a8152d7ca6580be2e693a051e9",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_a.biases",
"sha256": "53d649c6bb41ca9804bf56bd20be8855fef5d70655a41bcbfc5b8f7bb0edaa4f",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.20.linear_attn.in_proj_b",
"sha256": "2e69535c93fb34ecc21fb18df2cf1fa2850e721b8df565f533168e95b2abe72e",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.20.linear_attn.in_proj_b.weight",
"sha256": "5a679d13bc3b10de9853b389aaa5a1c311ec101bef1400332ccb96976026d8b8",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_b.scales",
"sha256": "ba117d7d759c3d447f99c60dc5fa4e84b97917cd7ce7a1a482d0037f95558c56",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_b.biases",
"sha256": "3a7f9b4584cd1575eb0220b633ebe68559ec29d67d8f09281d44e2aa2ef08bb1",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.20.linear_attn.in_proj_qkv",
"sha256": "d1218ca20df63c02fead5e5ca693c20f244d60fd9531587a2050f62632f09685",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.20.linear_attn.in_proj_qkv.weight",
"sha256": "86fc9830e883297618d2fbf443818c59492509002fb375e646b0bf41870267f7",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_qkv.scales",
"sha256": "ba3e5683a7f1e223002fd4c8e097697e9c077f528d670cea487f745dd655c496",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_qkv.biases",
"sha256": "8ffb18db49b2c95acab1bc0c6c542022395946aa6a99514570f29b413d24a85f",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.20.linear_attn.in_proj_z",
"sha256": "9e70f23863e92438be236b556441665ed63878b889f0ebc55a6f244f3bb740b5",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.20.linear_attn.in_proj_z.weight",
"sha256": "8d233cce9b7b89a3e297d2e594141fc38dcb9de86918d861ab1891e435ea6a8a",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_z.scales",
"sha256": "ab826328d1f515d56adf48ce6ccc17155be3c94bef41c1f1014a9bf077ad689c",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.in_proj_z.biases",
"sha256": "540b23075a0a837d8896bc41f9a50c2bfcb36a09e3c41313364d7a74f1bbb1a1",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.20.linear_attn.out_proj",
"sha256": "45c8a6bb855d55654cc986ea49fea999fffba8db2d6196d1ab56bc801d71993d",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.20.linear_attn.out_proj.weight",
"sha256": "39ee38c28edc0292330b14d635ac3a808e094cc3fe500effad145bdc5793ecb9",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.out_proj.scales",
"sha256": "b756796b1342722adb98d337ed8df0c9fd10d7b0119b57fc06135b532739cb9a",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.20.linear_attn.out_proj.biases",
"sha256": "d6b09d8515cb2dbac0411c312c42cfbed202fc3e9b1c3f1c03e4a347b5b7c103",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.20.mlp.down_proj",
"sha256": "c8950e343c71cd7c2cea48f493541a90e51641ceec1f43432e14ee87fc93e30f",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.20.mlp.down_proj.weight",
"sha256": "417fe4d84755187544f16a9533246af6fb5ba478d5cadc4ea80ebaf33c98e52d",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.down_proj.scales",
"sha256": "5876e744c2585b91cd86df13e7cb1735459cb4c26ffe487d752b0354ca701a81",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.down_proj.biases",
"sha256": "b7055c372d55f4eb1dd361b317d995e46c81b7c9c2806f4fabea7082169240b4",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.20.mlp.gate_proj",
"sha256": "443e4f318231b2c9c77b5e48dc372c3ef084fc562bbbfeead1116349c8668892",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.20.mlp.gate_proj.weight",
"sha256": "b5dbe353449218261fbfa0df8efe423ed8b90be7b37d2f41c736380f77c888dd",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.gate_proj.scales",
"sha256": "fc9b4fc78bd8f5573a01dd81c476527c1dbf9c07141dc175b4d120c826d9e926",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.gate_proj.biases",
"sha256": "3b0b299a71ba108dd974f8043156bbed32db65f9680c934cfdb227c26346412f",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.20.mlp.up_proj",
"sha256": "15145f9fc9ab09bb7af5053c99050254010efbead2d2e8ed407489a90ff5768a",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.20.mlp.up_proj.weight",
"sha256": "62b99a0b98513d45a7953bfdf75d1c67855c08fea3ef8917f2fe04edb6379f58",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.up_proj.scales",
"sha256": "02a0d16c499acf98aea020befb3188732706106ca45acf7cf01bdadb61f1ca52",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.20.mlp.up_proj.biases",
"sha256": "2e948f24b5b51ed9d33f48109fc281eb2ee0cc0012f0ef81b170c19e9fa25943",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.21.linear_attn.in_proj_a",
"sha256": "e8355bfcaafe618b8b54e57a453e04cd7ae2439b0a68bfb5e76146d9aaa802e7",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.21.linear_attn.in_proj_a.weight",
"sha256": "67181ec712cbced76ccffd08105fa1f28ba4535ec7477e93dc2bca581419790d",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_a.scales",
"sha256": "178ac895f19a698a36a2f6a4a0da0d9dd21649cce466a19d090f3bc49fdbb605",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_a.biases",
"sha256": "03b3e03ade734eccf5fb6dc292b83714fa6797d02919327dcfc3c1d4fe92374b",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.21.linear_attn.in_proj_b",
"sha256": "250c8e9ff7fc937ee3cc41110547f59eb5b0ebdbe05b320ecefbedbde4124766",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.21.linear_attn.in_proj_b.weight",
"sha256": "caa4b102be9f46f88f3e0a0850fdbf5a5de4b86d102c05bba2d4371de07b6795",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_b.scales",
"sha256": "1725756bf9748a05992121f872a3193e3063d219bf980befeffab125f48f877f",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_b.biases",
"sha256": "aed860c02baef928f4eef16d098a3bf617fefd6e43a66e34d5efd9062e55b3ba",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.21.linear_attn.in_proj_qkv",
"sha256": "94fe9ee7369818f8f08382dbb5f14713c0f334f377245584afe43fef65cac738",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.21.linear_attn.in_proj_qkv.weight",
"sha256": "70643edc37dfe7cc0358ba03b55c3f349e24f9b7d0aa74deb9bcdaf97e995e07",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_qkv.scales",
"sha256": "b3f2d664068499d4d09115a7e226ddb8ad184af61b661b187339f060ec09ae0d",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_qkv.biases",
"sha256": "0bce2387b986361651c2f2e5e5cfd6a92c723ee516eba3212caed87e604a6ac5",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.21.linear_attn.in_proj_z",
"sha256": "307639e590e528178e3d0ac7699e53a91a21ef777fe76b9e623de1a9a5066802",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.21.linear_attn.in_proj_z.weight",
"sha256": "511752172ef5a086ce2839f591f8cbbce6d8564df895303cd955724a6fc6eeb1",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_z.scales",
"sha256": "5a65a69a862a167be64b2925cd65304fdd0f44d575bc71f96ef9ed6f739983ba",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.in_proj_z.biases",
"sha256": "5b4d2519514909c68df127ea13509942dcb2efe804d85e336ba6789c57b74df6",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.21.linear_attn.out_proj",
"sha256": "26b0a58679a3118de8f55abc3819078945af4bd4e210c070707199873c59fbcc",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.21.linear_attn.out_proj.weight",
"sha256": "930469a8f2619c9a7741744be526159629de3d37e641beb95d42e373833e6444",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.out_proj.scales",
"sha256": "08ea3e5620101177f29a360c8ab35af5551ab5099ef289c9c1d81fa42ce0d418",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.21.linear_attn.out_proj.biases",
"sha256": "038911fe6dbc7346aa948a8f703a96894a3d17367a644f1a3bc7e3d8d1ebd46b",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.21.mlp.down_proj",
"sha256": "7c92642e31fa99c8d646059f428ee1b99284040706b813d5d1fe0485345bbde6",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.21.mlp.down_proj.weight",
"sha256": "ef1b50b860955adb8fc765a2418267f547c67d595fa61ee10befb1d0d24a1260",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.down_proj.scales",
"sha256": "a42b7f380c07cbb8c1c01ebfdab407e48abed9de3c424acd7388d568c22113d4",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.down_proj.biases",
"sha256": "e43db247296a086943bbeba5a8912b82cc93e9073ae7bc6224753248a1b57d0b",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.21.mlp.gate_proj",
"sha256": "7683d8870b1d8dbf4bf9718e410f645fa5049317de7573f048b0b12dbce20e79",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.21.mlp.gate_proj.weight",
"sha256": "ec2b24c826fb5a2d75bfbeef695202a387210ac47616b05054f828e1d79f2e37",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.gate_proj.scales",
"sha256": "59b640df0b4c9a4e8f8553eabf1890dbd64a7023bdb71bfbaf2e2bba724b4d26",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.gate_proj.biases",
"sha256": "d3bab269c118c65e35a44fb320189c87fe8c2b42646ac382bc57e76744682bd8",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.21.mlp.up_proj",
"sha256": "da4cba76ef9f40efad96ee69dae5455b6be77cd0a38626c5fd2b987b1fd64d66",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.21.mlp.up_proj.weight",
"sha256": "90725ba67878f77d7b115fe8500355fdd5a11ac1fa39a72d3148ce80242903ab",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.up_proj.scales",
"sha256": "4c73047cfa9b0a915ac3934bdffe8cf8bf5ba4dee969300f28cbb1061933b349",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.21.mlp.up_proj.biases",
"sha256": "83a5b6ab20b362c72ae60f1e14444833dc4e661c067588c7e99c3a2b12e1eb58",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.22.linear_attn.in_proj_a",
"sha256": "e63c4d90aa139c099e5a982a561c79edeb7a3f2f96a5232c2cec2ad1459e32fe",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.22.linear_attn.in_proj_a.weight",
"sha256": "f7275140fd723bb6d62312854e0cc6e547f11d00041ca314b5ce2739d528a4da",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_a.scales",
"sha256": "640bc15d53606d17e5232170dfef8b84cc890c09e5572076aae4f152490a2ab2",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_a.biases",
"sha256": "e2d98e5a5e817efed76754006eac91763cd7c2e1690393475b1d40be9a6ac315",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.22.linear_attn.in_proj_b",
"sha256": "1b992ab9ee15739d63aee2102f80d94845a8ae8dafb2ec8c58df7e73130065b0",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.22.linear_attn.in_proj_b.weight",
"sha256": "d6d25281ce7a4f5fb71ace44aff82e68f667619d47d8959a7f12bfd7dc4ce862",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_b.scales",
"sha256": "cb2a24033bfc97157fa98007159d3fed4a71363c017ef48ea6fc512a3ad0f2bc",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_b.biases",
"sha256": "b4e8d658dfc1e819a41822c4a6d4b6617360b842b1bd1b0b424e9e89eab80ce6",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.22.linear_attn.in_proj_qkv",
"sha256": "4d45662e659da2cbb371f26ebb0a06e7827caddbbf88cb89db92b465eece8f14",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.22.linear_attn.in_proj_qkv.weight",
"sha256": "4e5543f031603b2d1912762df9f93d84149a4413fa83fe51cb21a2db18711a7f",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_qkv.scales",
"sha256": "c28135ffbaad32ba37049b70fc02751a51ab1c4daffc03dc1e765f9bc20656f2",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_qkv.biases",
"sha256": "9c4fd9ff864c08cfc5c182575e6f22970b9c3dca0fb2ef32f0588800dc026fc2",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.22.linear_attn.in_proj_z",
"sha256": "6577f66f26777758e4fe5dc84bccd6ee19cca179c44b240009243572cdf378d7",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.22.linear_attn.in_proj_z.weight",
"sha256": "6710438fc3a9fe0c4f633a4e67c3c096cfce436fa737f2b1c585ae451b40433e",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_z.scales",
"sha256": "bfb9ada3c53a6b928d08c1620bf6aec9cfd2372aed05fac7860afef2e6922a99",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.in_proj_z.biases",
"sha256": "dc40d553e6eb37fd1e7199789bf9b768739b30efa75dc0cfe865b297fa22b36a",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.22.linear_attn.out_proj",
"sha256": "19c62d560f8c0e64ae880f493e613e553686784094979984d0be85a95273820d",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.22.linear_attn.out_proj.weight",
"sha256": "747923c727f8b712323d106e08a7813a0ba19676e03142b225f264f88b2174b1",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.out_proj.scales",
"sha256": "9c0c9dc6c543cb1809cada3f54892bc3d8b46790289541811ed7e83dd3f4dd9f",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.22.linear_attn.out_proj.biases",
"sha256": "8c8210a61f27f1b6814f35fd914f3313bfece1b57fd4bf385141c55c007f91f6",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.22.mlp.down_proj",
"sha256": "0322f9703857f031db341e9e3b4caf0557bf74663cb3a4aef39eab4283d7840f",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.22.mlp.down_proj.weight",
"sha256": "8c407d6587f343df1f624a69864ebd48582b33820f2e3c7189f5f6653d83cbc3",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.down_proj.scales",
"sha256": "73b829bcf31cfa580e877aa12e45b9658230ac4e5e14b043e4c757ac1f0e2179",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.down_proj.biases",
"sha256": "0ce8e24ec7f4c2d51bcea2ef8256e69578ef7ecac5d62ab58f85f39b94b35939",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.22.mlp.gate_proj",
"sha256": "bb7bb4fd24a7760ad9c69d9d5b276a67aa7816e4f6c9418a459c821c8bb82d54",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.22.mlp.gate_proj.weight",
"sha256": "9f99ce5dede0468807bfb28590775cca3ac70c12e6db58913f26643656a5929e",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.gate_proj.scales",
"sha256": "27b40fbc847e2fdba7625431b509ef3f268c44a1dff20c96b0806687e916ce89",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.gate_proj.biases",
"sha256": "443627429e1ab823ceede29e29400eadf7958b0f82d99672d9ddebd913359beb",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.22.mlp.up_proj",
"sha256": "6b02e91348a1045ceef325ac50698328937a161bb9f0f9ec9ff34ed20fcdc724",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.22.mlp.up_proj.weight",
"sha256": "cff8c1185fe9eb88f07e41d35b9a18e56ed3f8f710cac8215ce1e24b4efa75ed",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.up_proj.scales",
"sha256": "3a92ca89801db18b169fb4769036557a956cd84b610f3e1a1ed69d8b14017de3",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.22.mlp.up_proj.biases",
"sha256": "90ba196027ef685af529cd559c8b08aed6db12262decadf47507a05175b57c3a",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.23.mlp.down_proj",
"sha256": "d46d78ff2372b592283126966ca598167c48aab1cf521f0dd72b7db247c1dc96",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.23.mlp.down_proj.weight",
"sha256": "ca1616fa6ed74a79097dc44356747746e022adf18458ceac19f75db52af796c6",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.down_proj.scales",
"sha256": "5ff956ab53da107b4811f8f139eb51c26711fbb00be6e17b14391a4852b3a090",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.down_proj.biases",
"sha256": "2bc525c4abff5fed60cfbd64b43e7b6035327a12692367e5d9c76d179b8d0674",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.23.mlp.gate_proj",
"sha256": "a95b2c5dcaedacf3f8cef34c6d763471aa92b2bd0319b8c55cd237692b675ef4",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.23.mlp.gate_proj.weight",
"sha256": "1498d41563de94c6ec7f9798e0ac8549e8f5008cd916a52dacd3e9a4cfdbc130",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.gate_proj.scales",
"sha256": "53a982d9e10f6636c5b44dd95dbc4b79a5a5dd23ca12491121060d9ad5cd8052",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.gate_proj.biases",
"sha256": "602d02430c966cb5c61e6685d0d69363f0d137e4be057dfe74a094035ec5d44f",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.23.mlp.up_proj",
"sha256": "5c1048a5fbcbe3afcfa6603e4fbe96e19381ca6f4d9886ccaeaa421fcb92cf14",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.23.mlp.up_proj.weight",
"sha256": "c80a11f099359a5a2f72481c4dd601e66b3d364a3f9c505aed1d07f11cc38642",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.up_proj.scales",
"sha256": "0dd13d91d504cf6539250d8e02887fa42073085e475004b9fb2293a4e522ee34",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.23.mlp.up_proj.biases",
"sha256": "107c81f5b276b0d101c8328495063536b2055670089b54b759b31401e649f563",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.23.self_attn.k_proj",
"sha256": "5591d5db533a4bd7889ffd88a88a9ab225337f8571f9f50af1268a7690606500",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.23.self_attn.k_proj.weight",
"sha256": "b0f7d98ca4620e9d7c35e14425537ac5ffe3b642553d146856863ea022fc291c",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.k_proj.scales",
"sha256": "64024c7e4a0f664b7593b92af5c65a8d4f1c6f339ac2f32e681f1d6e3583359c",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.k_proj.biases",
"sha256": "3f6104a0113929b4d3ff951f15f34470c48b0e1e860ef538101560c58f420cc8",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.23.self_attn.o_proj",
"sha256": "1e6f0ccd61c3e7995b406fa3a5bbd064a736302a36b4e184d86d23dc83f86c2a",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.23.self_attn.o_proj.weight",
"sha256": "47a802699a657a69e2d4d9952e575dfa9ca99d9637921a7b2287cd7f9ddfe16e",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.o_proj.scales",
"sha256": "3f5af46d6a014e04ac73fcd1999b5247b60c97e950bf49866943f130b9bd0511",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.o_proj.biases",
"sha256": "6e9ac7978377adf3eaa1a4c05d7c36867e8014bbe3df52d37733250756d87baa",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.23.self_attn.q_proj",
"sha256": "0c0fadf45b7b82292932ab373ca89b6a5d30a5ab85e196e24ea95696c74edc5b",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.23.self_attn.q_proj.weight",
"sha256": "372008f7f2e0469a3ec98fbb94dc842219f75dbd47bf6b7e9c8c8bc075e49ddd",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.q_proj.scales",
"sha256": "766e450b0040adc02200a84bd08c4ffaca1c754c0621bf0ff7148c851d886476",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.q_proj.biases",
"sha256": "8386319491c16e36f830601f4aacda51e88a282479dd98ac1d8da1f535060930",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.23.self_attn.v_proj",
"sha256": "eec9a51b312f7b5e784693661819a9c3fe67816ab88ad00816421f4304b444e5",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.23.self_attn.v_proj.weight",
"sha256": "5671e3abe5eff1c12664374aa52ed50f7a28c239bf8e74337bd80fd8739e61c9",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.v_proj.scales",
"sha256": "a6541f65fe27d3cb127300b31b65af684ef187186ca8d6cc20a111129e01ed9c",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.23.self_attn.v_proj.biases",
"sha256": "71c3af2eeca838a669734c9fc0e9ecbc3da4be4eeadeb6785f7766cfa2e02737",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.3.mlp.down_proj",
"sha256": "e52c4f1e61a08fc580ad2ff160de8ec0f533941fc1faa3d2253642563774e7a0",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.3.mlp.down_proj.weight",
"sha256": "a63888c3b7ec3f4303a9ab6bd0ad7379da74a7bb2aa35046f3f695eb70eef39f",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.down_proj.scales",
"sha256": "e3b221a5ac9d004f445663b4a2e773c1c98b6ccd518b251dd500b1057bb3e246",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.down_proj.biases",
"sha256": "dfbc5979a3a50aea8490570adc11b7fe10d88724364602e0ebb17b15156e7cde",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.3.mlp.gate_proj",
"sha256": "e43d3216f5b485e6b181c7d405cdf3035caf505134e44ad615f66fcf2c46ee39",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.3.mlp.gate_proj.weight",
"sha256": "87867389f946be827457df179c757fd0bb6b8c9ca02e7416701712f01c8022a3",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.gate_proj.scales",
"sha256": "a718ff2d60f8441676768cd9d9362219b5c609879e5a7a96e88ffc640417643a",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.gate_proj.biases",
"sha256": "61aefa701e1df1e2bf85338f198a358b48162a35b1472c189cbd9951648c0c7d",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.3.mlp.up_proj",
"sha256": "1c71aec873427a2cbddd7d3a92512b88bb1760291f7230dcda433f24c127f25f",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.3.mlp.up_proj.weight",
"sha256": "881f960d6c7cc2d6157d45167628b8a1ea5f782e9f5966bcc7338682db7e59fb",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.up_proj.scales",
"sha256": "e0ceb5235d1e5693da79cf44f243c04cefb222dfefa26068b777c0f08ae50fc9",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.3.mlp.up_proj.biases",
"sha256": "f78ebbd65a2545fac8035fd0fe17e239f30eb7b88dc5d26dd42a05b269aae969",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.3.self_attn.k_proj",
"sha256": "a7935ec38341ecd669e6f63d953d5d0672a0cde4f909906f67c816bc35b48f57",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.3.self_attn.k_proj.weight",
"sha256": "8078f35dee7aee4bb83efe71675cda6b39b905436834724e1c8caa1047c1adcf",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.k_proj.scales",
"sha256": "a6f9984ab99bc54419b7688e1b742fe84e6ceb27594cfd7c9b42771668f4d7e6",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.k_proj.biases",
"sha256": "6ac47a6214709830f70c6e2cc2b2fd088fe50a3bc35fc4bf372de6d20556e88d",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.3.self_attn.o_proj",
"sha256": "89f17db89642f0cac0ae06e1fadfd91f6328275658514d833fc2e9edbebb78ac",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.3.self_attn.o_proj.weight",
"sha256": "4d6e9b9bdb21b7b643f70a12fa81cd1d44ff249f460a2e37656a4a3bb71ad6cf",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.o_proj.scales",
"sha256": "72df975c67e891446e8a95d9f13235f4e948ad80d007fa24eaaba9e5b389d063",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.o_proj.biases",
"sha256": "fd45f83080b24cdcc09b459a54b82994b0f8c3b1fad655a6f55ec79ab0554a79",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.3.self_attn.q_proj",
"sha256": "52d5f351352d42dc1d3e9aa5130dfac03bffda18f0e6d55235c071d15f58b31e",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.3.self_attn.q_proj.weight",
"sha256": "4e042f215f6cb33aa315456981fec850ffb3a3d087dda57ec46aef055cf3ddc0",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.q_proj.scales",
"sha256": "a2fe2afc21fd6651bc41d4121a7fba79f456139c96043ff524cf91e61bc6b3ac",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.q_proj.biases",
"sha256": "adba5e4070b04a700a3c106f7e0dfffd25d5e0788be896ef96b3ff2ed459add0",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.3.self_attn.v_proj",
"sha256": "1b923a9c9c9fb9df1e2e7a83bc20ed5fda293096fea054137446c12a60a43f4e",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.3.self_attn.v_proj.weight",
"sha256": "0b9faa71fe02be2b13f71f2d4e0e0e12ab21961b0dad4c964d55420fe113afa3",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.v_proj.scales",
"sha256": "a04242f028fe98f2b986457545ee82a1770e114d88f1440f7d8032071957ba1f",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.3.self_attn.v_proj.biases",
"sha256": "fcc0f9a875cd7a9b56de236fbfc39cf6f4e52109fac263a69d2de287b8c067a8",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.4.linear_attn.in_proj_a",
"sha256": "d054fc226174ca503d19c9400f33d34c2012f6de7b9797469dd13f664f5f3ba0",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.4.linear_attn.in_proj_a.weight",
"sha256": "020a09e8daf303ffc57cc26e760541bf4a0993d5d0576bc50d9fac0d3f549b3b",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_a.scales",
"sha256": "2d1179b7d823decd3f1605a78fe606083dd14125b83e9095ac7645fc605d9de8",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_a.biases",
"sha256": "6f336d2fc4c2f93ebebf5d46976238bac61e8aa5b617e849cd70f949374e7e85",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.4.linear_attn.in_proj_b",
"sha256": "d77dc4fae1be4a347b65518fd3c87c42d21caca025800841774984493cc689f0",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.4.linear_attn.in_proj_b.weight",
"sha256": "5f09808758b5bb2d78686d2ef5ab2a20c3fd31c966d12d9e8c2e80720c0f0c06",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_b.scales",
"sha256": "794c06d9dadf9304480d8a1ccbfdcc9a3ab036796b1f92f5034d98d97c46ba1d",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_b.biases",
"sha256": "816d3d39a797cf0dbd0d344d3baf91013ecb38d74087338c72aa8879ac9300ab",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.4.linear_attn.in_proj_qkv",
"sha256": "d662215388658792d12f2a3f54a122a9e8059c8448905c42d0a61fa31d86f0d6",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.4.linear_attn.in_proj_qkv.weight",
"sha256": "d8ecb82fdc590cfa44e582f7192e01ed5096e074a52a52f3ec816847a2579156",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_qkv.scales",
"sha256": "9e2dd6c801d3906c30b7ee9a6d3052027d520b25b97492aa81dc35abe5adf01e",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_qkv.biases",
"sha256": "7ea57757755fb47eeab92412b0e346706887005940285623c03bdd3292fc7e57",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.4.linear_attn.in_proj_z",
"sha256": "d6cd4fabc418351bf689fe5fb9141581f675c69dfc43280cd5abd9665afe7d86",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.4.linear_attn.in_proj_z.weight",
"sha256": "0cf119d0b0da5e268315aeb534533637979515fe49a2f7f4e63a096e1fc0dc2d",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_z.scales",
"sha256": "edd430ec78f716bf981341cdafe5cc208b425e5f826f49ce98318f62927e743d",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.in_proj_z.biases",
"sha256": "2a77837b77b7eef028f15b6545c20fab878451d66f9e183a57813d36d55c5967",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.4.linear_attn.out_proj",
"sha256": "06e2f7e0a83dbe028277d7795071332b67e38422fc43818af29838b0d08d3c36",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.4.linear_attn.out_proj.weight",
"sha256": "bed7ebbe2bacce0c2cbe21d697a317060cf94fb56000abba01adb05025d00892",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.out_proj.scales",
"sha256": "324b23750f2725acd268926d71bc6f50254344631cd22a3765ad7117ee5c8b4a",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.4.linear_attn.out_proj.biases",
"sha256": "ecb3bb3307f7bb78d7ada31a280c2d03b180e9cc09bd690d6104bee72d1311bf",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.4.mlp.down_proj",
"sha256": "e796d5fd3b26383d79f1da97051af2492d88e50edde50ed0f245d581c35326c7",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.4.mlp.down_proj.weight",
"sha256": "4e3bf897279fc4b3c636fc141418e5ffae4bf31c351ddbc80e5b1d54c1b7122a",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.down_proj.scales",
"sha256": "249d8e195aa9829a7b6b3739f096f613cc931b6843b4d8eeb33f4c4bfe264473",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.down_proj.biases",
"sha256": "2d8e2862c2a267f427018aa0de4cf4c9592b61e2eb8958d8956bd45d17982e1e",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.4.mlp.gate_proj",
"sha256": "6d4b6dde2472d398cc92ddc570510ea78937bd25a1e4998ad861e92908f5d2b1",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.4.mlp.gate_proj.weight",
"sha256": "a9413fbc87b7b0c79b14c28deb12303fbc68df3b0d22d49db91416ac8cbe38ae",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.gate_proj.scales",
"sha256": "46e467ba2a6ba97f198d5bdd355c53d824770b374ed23892e1fe5ea5ce1a406a",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.gate_proj.biases",
"sha256": "e8f073b3a0107023409d58c055a7732f6f7bacc74c947db232fb747bdcdfb41a",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.4.mlp.up_proj",
"sha256": "1ffc3da06f4c1b5d0bcb4f3d2426c71230511fc9ef452c7f8b75d3b1bba455f5",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.4.mlp.up_proj.weight",
"sha256": "e68dcf663362f07818bf087c89975f1402f003615b691274e38687581507c3ae",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.up_proj.scales",
"sha256": "b3e39d2309c9f6cca107c711ed4e6350bb40fdfb1ad8ef5d6e5d67465784af07",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.4.mlp.up_proj.biases",
"sha256": "dc7b28eb494c567e42c8ed5379b8895f7674998cda3bd4f71656e1e79ee08787",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.5.linear_attn.in_proj_a",
"sha256": "89649d1bd2af89607eebf9ed86ffd23cf8f0706bdd26f707bbc4f017f2059a9f",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.5.linear_attn.in_proj_a.weight",
"sha256": "0de06e76b987fb4072744f8f9ac9f1e63b171ccdcb5c2b2fe2623f9210b0dd81",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_a.scales",
"sha256": "648d1927b098499a9dd5fabba3c87f5f3cadc3ff326191e8be0008c7fd50cf74",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_a.biases",
"sha256": "adfa14d295ae70347ecc7ea2975afcfa63a730560e2cdfa715801b1b139d06f4",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.5.linear_attn.in_proj_b",
"sha256": "40403c8e1bcbacec5e916ae8736f2c2c484e361f6053d4cae5ae3d54343d7ebe",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.5.linear_attn.in_proj_b.weight",
"sha256": "d553d981ceb6acc51ad0ec034700b4e6a264c935cdb6cf4ebf961d20d82d5b4a",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_b.scales",
"sha256": "19799b78439d6ec8680d174103878e7e3d55d1624df691b935365e65e44fcfa3",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_b.biases",
"sha256": "e0b1c9d237b2f4b74a28eedb0f7a27c3cbea386b352dedda868ce6a2168d3439",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.5.linear_attn.in_proj_qkv",
"sha256": "ae27bdbd974695f1a02dc5afadee33c577d387bd9c5a0c3756d1c182b9901de8",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.5.linear_attn.in_proj_qkv.weight",
"sha256": "f9d9659209df01953f271223793274c852b98e01bc74c457ee14182a5e70474b",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_qkv.scales",
"sha256": "b93c48a02b04610b696b5e3597001ec22bfbd81208d09895320e72af1e29d3ef",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_qkv.biases",
"sha256": "9b2d707ddbb1089bc77f7e2b524b9844d70946ffa90c3273151a2ba3ee8a375b",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.5.linear_attn.in_proj_z",
"sha256": "af68371e5093e7b7c524dfe0b2855b62d5a735859e6228c8becd56857f508045",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.5.linear_attn.in_proj_z.weight",
"sha256": "8ecae6939464834d7c0208632ca69167611194f2f0474327278f4448f1c390cb",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_z.scales",
"sha256": "dc30536de229f2027c37c2fe2a243333f89cf5adde843e4dc243fa6d258b2721",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.in_proj_z.biases",
"sha256": "a1b1664e52621ecfc2a4bd70494f293065558237c69ef8f7dbf424a94070bca9",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.5.linear_attn.out_proj",
"sha256": "3197cb0e4b8603f28c69fc483305f74cf2984654ac81b535bb4b95b44c4b05b6",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.5.linear_attn.out_proj.weight",
"sha256": "b51b19c4df1fccd5b595d4b164274f670e1f325e376ffaa014bdde95a1cb0348",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.out_proj.scales",
"sha256": "19e0c0beb886e9c66098cb2e6aad06efba5a0f0dda1574d731131c5f63a37faf",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.5.linear_attn.out_proj.biases",
"sha256": "99d33541dcaf80ff0a1e2dc80deefddd6863509fa3c35deed5b0b9003186f116",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.5.mlp.down_proj",
"sha256": "55967378473916c9ec6ba6fb14be5fd80f1a5e391b87c9cf27577c5ce062de41",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.5.mlp.down_proj.weight",
"sha256": "ee536b59dced896e8e986ed1e08c961b7b820c3be8c666fe72a2d0641851aedf",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.down_proj.scales",
"sha256": "81474e51ecb0cd913f40ebaf7802e3bf944c73143dca99487c2984a41225b6eb",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.down_proj.biases",
"sha256": "b33b76df4c3cda2806e297f10457ea68ef656b6f94e0fd7432c07d00c6db0f4b",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.5.mlp.gate_proj",
"sha256": "6e8738cb566a471901d810b021ddc882cc20ec10585b397552a53627d51ff1c6",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.5.mlp.gate_proj.weight",
"sha256": "b9c1342cb97cfab892b6e2caa7382a240a198598a399eb72e07df0d3a2d6aedb",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.gate_proj.scales",
"sha256": "14ad9e4af33ecc9acd3c010baa7e0af1956c1b85d8f1d0109044d4f55a2c52c2",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.gate_proj.biases",
"sha256": "9ef25dc584928ba13fb80245c60e1e2ebcda86a68efd21b5f72917de8a7055f5",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.5.mlp.up_proj",
"sha256": "eb9b71c20c3fb12eb6faed719fe126e2c72a573a3a81861700467e10e21a02c9",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.5.mlp.up_proj.weight",
"sha256": "5934306d0f9bb56cd0b1db19f078ea15ec1bea1a4cb41be807ada4a621a567f4",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.up_proj.scales",
"sha256": "77c3016660fec293a5022b4be78bc45197e4ab9ef9635d858e38d59e71dda25a",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.5.mlp.up_proj.biases",
"sha256": "feeb6064c532abe840c6aacd67845edfdd72d0d486738dfc5438b26c8f962152",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.6.linear_attn.in_proj_a",
"sha256": "367ee2974f4c1f312c3e72044df0b950fc2fa91278c6d854ada7e4558816af50",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.6.linear_attn.in_proj_a.weight",
"sha256": "5775ab03fd07a8275bfbe67bce5f1ac803feef4a420f772756fccb992186dee1",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_a.scales",
"sha256": "74ebc115ddf46664adfc568acf79647bac817945c49d85bcb2b886bcb67438d7",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_a.biases",
"sha256": "7001d585840f45bee96ad4885a2172a61efab7695469d3bd13f683dad7815c49",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.6.linear_attn.in_proj_b",
"sha256": "4e1e11b97258836e39502e44e0d4c55f1bfa2b2cfee8b81d14a8bc36c3ab75f1",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.6.linear_attn.in_proj_b.weight",
"sha256": "fba31abfa3d8ffb82006afffd7ae605289ff042d397c6d1501fec3cbf73ef095",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_b.scales",
"sha256": "c9898c7350978cc7fb2d706792082d1ef3ef07638a6250a9c019763a3e0dafb9",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_b.biases",
"sha256": "7ca2c447b2739f6bdf912e25bcd3b582f3c211cefe036ca507052000e9058a9e",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.6.linear_attn.in_proj_qkv",
"sha256": "dbaee8e4e106acf090c84cb518e4c4c773afec258ad3c2585a92a883bc34a704",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.6.linear_attn.in_proj_qkv.weight",
"sha256": "1e7126dfc7f9029c4edcb273dad27d72bf5ecf269e68b0dcf5405bc0abaf2979",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_qkv.scales",
"sha256": "a033f79f71454b576d63482a5494202cefd4d02f9aac4b6c43d39838b3c59373",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_qkv.biases",
"sha256": "bddaefa6cdb8f37d9608571c598b060e0c4deaba3d42900ad5624d0aa9fd25bb",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.6.linear_attn.in_proj_z",
"sha256": "87f0ecfb63d9b4d00b33848033cef1f98a627bb431fe0852b27c755676c6990f",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.6.linear_attn.in_proj_z.weight",
"sha256": "b118de3a5f25f554793a4ec88acc38863af4854226ab005112a998cbb34474a7",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_z.scales",
"sha256": "e9364d4811bb9aa5fcbca08996697de0a4bd64eafc16aee0d61484ff026658c0",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.in_proj_z.biases",
"sha256": "c3e2f6ea8ce9d29566020a39dea171bfa5139963323c1c623421a77a75b0fda9",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.6.linear_attn.out_proj",
"sha256": "43a2143e8504d1e07d9644ce23201804d7fd1b6343df9b63c7e9d1eeb544d21b",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.6.linear_attn.out_proj.weight",
"sha256": "3cc3604b67b80fc91edaec21110df518b71496bef4fbc5d241b22d870b16c3ae",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.out_proj.scales",
"sha256": "58cf091fedecc5b99c3e38fee844659e5ade4d938ffab44b8c7725327914ad68",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.6.linear_attn.out_proj.biases",
"sha256": "61d088489d1cebca1f7659ccedbfbaf4955e95a1a671bad6d86e5bcb66d3154d",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.6.mlp.down_proj",
"sha256": "7d570695657aecaa350ae9ee60dbee0952d614cb7e6f05f3524daeb95f1c3a8a",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.6.mlp.down_proj.weight",
"sha256": "93968b3175e27fd49463db42ca21ac68147ff13af360bfc41201c8b640e4f436",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.down_proj.scales",
"sha256": "08b81a04bd34b2124dc8cf57274925259fe1b1396b2c7b4fa2a337fb207e9335",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.down_proj.biases",
"sha256": "3dc6e0824ec96b554096b2ff427d00ede88eecf21fe32b4c0a3e5647c18ea36b",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.6.mlp.gate_proj",
"sha256": "9bb0638893469c29c0f654bb26396c0e4abea66b54de6682b5efa96b4eb4faad",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.6.mlp.gate_proj.weight",
"sha256": "95717118e65c200657e2ce3e2b1e9970cf3695d9362b0896c74a17488e021483",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.gate_proj.scales",
"sha256": "a0834c137f97f90484ddbd553827169114be5803d1747830cc91bc5ec7396d32",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.gate_proj.biases",
"sha256": "586dfabbfcfb5ea63753e47911080ab806a251246e866342f85ed278869eafd5",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.6.mlp.up_proj",
"sha256": "60053878b8cfb45a5f87521e92f7517987e05923b2eaa83e26efa04c849cd618",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.6.mlp.up_proj.weight",
"sha256": "640139f90567a57bc1a3c4e00d90eb6668114d0d9392d1db8e8dc6118cf349db",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.up_proj.scales",
"sha256": "41771a8c359cd9d0d95bef86cacdcb6bede13292bae21de2d999d196b50a1abb",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.6.mlp.up_proj.biases",
"sha256": "edb0480b3430ddaadacc862908e586862574ce96e73b3e1eeedcd4ad1efd888d",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.7.mlp.down_proj",
"sha256": "6f0a0c884c86d402a497265c6dd3664dbb5ba7659393415e86a33cc061227018",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.7.mlp.down_proj.weight",
"sha256": "8cb556299f453321a5721685187521df1d2e96b69f9699d2b3b2554b166c11ee",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.down_proj.scales",
"sha256": "bd4eda7ff72f4e8faa32772535dcf8872c57e2e2aa08144fd0351f7ff5a57586",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.down_proj.biases",
"sha256": "f601e5202092dfafbd4d605a057315ea20ce8372222256fd40a86742aa852a9a",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.7.mlp.gate_proj",
"sha256": "545b72222e14dec17f357d994d95e72d8151529b48147ed877b2f40ad04794a7",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.7.mlp.gate_proj.weight",
"sha256": "b01fed51fc68cd8df1d7db78b75fd02848fc6ad4fe6a8f9a690f1d294343e7a2",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.gate_proj.scales",
"sha256": "2009d0db0c7058616d9abba359e2efb145c4f801504e4a221c83d48586ab941a",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.gate_proj.biases",
"sha256": "f6a78c5fec6a2d69bc05f0982e06db4afe6436b0ee0f910a808d19cbf13bd46b",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.7.mlp.up_proj",
"sha256": "6969162eafa282f3fb23a9a6ea8c72702fc2c70dba16b730b14bbabc6a44d3cd",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.7.mlp.up_proj.weight",
"sha256": "cb69fe6dd013322b02eb215bdc37d2c0c04ab1ddd06645f88fffb8cbadffff20",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.up_proj.scales",
"sha256": "541c3b340cc7a368dc42dada8976bd0d0beb9c9fdee1023770f72907a08522d9",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.7.mlp.up_proj.biases",
"sha256": "ca6fc76e0dbcfb6839aeb52f19ab4e8ed53c15af6a8323febb7545b3702b8b1b",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.7.self_attn.k_proj",
"sha256": "59fe87f66be68674b657b424db2f57260f1aa8f1f6a17ef54890c54b362c8ba7",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.7.self_attn.k_proj.weight",
"sha256": "7c8beffdf057946548a0d6752ee990f0732ed716d736704501978b1dca983d17",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.k_proj.scales",
"sha256": "f07809e5f357e6dc054131fc3da213ff2650874c45494ce00493362afc18967c",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.k_proj.biases",
"sha256": "8b84f193e41d4ffdb673386b22e2321b44a28774a8329047bd28e2b1153bedf8",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.7.self_attn.o_proj",
"sha256": "5ed8ddef7358f7af39fd0f1a62e8b6c1f9b0c16effefba47c4ef3fb4003847ba",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.7.self_attn.o_proj.weight",
"sha256": "94187afff3b33c678f94a39efa30e3976cbb135e475171820e2eec98cac2dd42",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.o_proj.scales",
"sha256": "aaf0f96534f966f0ed46c42b585b00cc896b22fa3df40c78b35b4ea016dd34db",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.o_proj.biases",
"sha256": "953c585fda039b58fb7d569afbd47e37c9cc84a5df7eadae33cb1179b1263247",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 6815744,
"groupSize": 64,
"prefix": "language_model.model.layers.7.self_attn.q_proj",
"sha256": "418e8ffac9232274c3f444bb256a0e590bb13092d13447ee13cead0bffedf6a7",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.7.self_attn.q_proj.weight",
"sha256": "9541fcecd4830b3dff08a8af5d622fb5b7aa7c26668bfb011bf7df8dadaf5afe",
"shape": [
4096,
384
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.q_proj.scales",
"sha256": "73e597e9889e8bf264b2d47a822aaf7548d454363c1286ea9db388fd03af6e16",
"shape": [
4096,
32
]
},
{
"bytes": 262144,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.q_proj.biases",
"sha256": "692878f79fae48de56723b385abf7696fcde5215e823eb2c37a87cc5e256e62f",
"shape": [
4096,
32
]
}
]
},
{
"bits": 6,
"bytes": 851968,
"groupSize": 64,
"prefix": "language_model.model.layers.7.self_attn.v_proj",
"sha256": "c9dfc38c7996042cfd3f1ff26d46bb37977c769c0d9e2b202cd5205bcb18b0ab",
"tensors": [
{
"bytes": 786432,
"dtype": "U32",
"name": "language_model.model.layers.7.self_attn.v_proj.weight",
"sha256": "ec8bf453fe69df9bb56533da9e73f81843b8fe438395d68c9da99e9950025a47",
"shape": [
512,
384
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.v_proj.scales",
"sha256": "696c3bc4a716335d3d07b6f13199db3d2a4d5e428a943f5a2edfa2a39a407640",
"shape": [
512,
32
]
},
{
"bytes": 32768,
"dtype": "BF16",
"name": "language_model.model.layers.7.self_attn.v_proj.biases",
"sha256": "d9f1b719e8c2f0d22e7a24b9b30b55d4ee3c99b19766e69e3bc86808d61820c8",
"shape": [
512,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.8.linear_attn.in_proj_a",
"sha256": "f0117bf0a95b0b11a0b9ed38e8f2fd636ce022ce345e8da697cab97ddad6e660",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.8.linear_attn.in_proj_a.weight",
"sha256": "ad35ed972f0c07813aec2e86e027b4264560d29b5c1f200e1a6e6e73d931da94",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_a.scales",
"sha256": "7c0d1ff5aada2c2bf876feb9437b0a32bc810378068eb71173808984e3d38a82",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_a.biases",
"sha256": "4424beb144319449fe92d8a9e85b57611f2abca54c0f58228f8e3fcc203a30af",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.8.linear_attn.in_proj_b",
"sha256": "a3ecdd5dd558fbd12988cb2c28dcbfc04a0427b6b1c98e19b25eb1dc412921ec",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.8.linear_attn.in_proj_b.weight",
"sha256": "eb102f187ec7ec240deb247cc9a9a97ced102fb6d7339fdb50f93ebfb01122b0",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_b.scales",
"sha256": "2aa69953883330dd17d5195ffa78cc4f55548772ad9ffa775f6f1f76d2b77e2a",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_b.biases",
"sha256": "aa711eabffd29921e51b141fb86ac085b22a9348cc4a50d2a5df787e4fa50246",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.8.linear_attn.in_proj_qkv",
"sha256": "32b3580009ebd73cc8ec1ab340b261806e8334f26de9c5eefb80ead047aa9a1b",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.8.linear_attn.in_proj_qkv.weight",
"sha256": "4222045c7163fac5815ea9546f34882edd2bc9ebc35548a3e40848056bfa11a2",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_qkv.scales",
"sha256": "22ee3855fdbaf907299178b21ad6a0abd4e42210676575bff09f654fca94d2e3",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_qkv.biases",
"sha256": "70d4e75d4f62f476d8a3a97492714b91f6d88d61432d1ea0cf1fa35f41d45003",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.8.linear_attn.in_proj_z",
"sha256": "1694c33dc6d11aad1a8481261d549a1b74deb96e86a781f903377b91be00b412",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.8.linear_attn.in_proj_z.weight",
"sha256": "fe5bc0d495d88b5f3b44be412fc8f8a5b260821fbda900de22b0c1b50177fc40",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_z.scales",
"sha256": "10ea4509917dadc9dbbd037183e0a8218303881e9f0172a5a560de3a9850ab09",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.in_proj_z.biases",
"sha256": "ea1a139c1556e9acf542910ed4eb87de6a0b84b519b1abadba979990931ba7ae",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.8.linear_attn.out_proj",
"sha256": "f728d9ae5312a1509f618f19348cac6e2a4f4a4ddcaa94fa691f1c950dbca937",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.8.linear_attn.out_proj.weight",
"sha256": "184e4ec87e00576c9a6eb077f43c1607b1a3a4f630ad0d2f8e68d46a6c5ccd43",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.out_proj.scales",
"sha256": "80296f14af8c6d3b976177bd4fd1da35e93c8d3dff82a509d868e2bea87ffd27",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.8.linear_attn.out_proj.biases",
"sha256": "009bac5260faf58eed048d7ae347bd58e885470642058ca89d8c4084b910cfcf",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.8.mlp.down_proj",
"sha256": "ff178c1e7a9b8819f77cdbe992f16cb65e2037dcbb247c20ff348947d5b72347",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.8.mlp.down_proj.weight",
"sha256": "b244da70bec807b18dde2c7d8b0aae28f763dc6da064b535a0d2080d4f7d88fe",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.down_proj.scales",
"sha256": "365c3252b93b13a373a8611e9b149e6c7393843d3ab3a98de70e5a96b89c5905",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.down_proj.biases",
"sha256": "568aee4f31d2c0fd37b88fc73ca39be8d89cd78f9378f5631be44fb1520c23a7",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.8.mlp.gate_proj",
"sha256": "660dd35182d453d9a9b13a8a72783bbf0637b3e612f5db8889d6f4bda89a3672",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.8.mlp.gate_proj.weight",
"sha256": "8b4c50165336dd760e2f20bc98436dd3176dfa9eb18f090597b143e85b7cae94",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.gate_proj.scales",
"sha256": "9d4a1d28412c00db820eb015c1579d5d443923bd256db754c8f6b8677c2fbb0f",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.gate_proj.biases",
"sha256": "913a9e9fa83a6f4d550860513ec9d3041040acfca838203b12d7d0f42dc2c626",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.8.mlp.up_proj",
"sha256": "9a0166abe8d1cc5befe53e568aaf13372981c8d4249ea76da812a795fa2ed3c8",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.8.mlp.up_proj.weight",
"sha256": "bbe35475bd00019712536884d322438ac93173c2bb68c83792ad1f19d60139ab",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.up_proj.scales",
"sha256": "724ac57a0b3c147592a6bfadd63de95b627447ff35da9fe5fa8d2f2318346ac1",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.8.mlp.up_proj.biases",
"sha256": "0cd77aaf61c84c583c4acc6d37dd3577b004f5403b162b741863c05e64d95f15",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.9.linear_attn.in_proj_a",
"sha256": "c11f0c4addf243474d558274ce095cc49b958c5c715c927af22cb3f0c834916a",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.9.linear_attn.in_proj_a.weight",
"sha256": "99f6b3f980cc7f6ab06cb57c42d112b486cf985cde5555262522d396dca68f0f",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_a.scales",
"sha256": "ac8ab971b21473b718a832f2e82393689b0b100ae83af7188dfaf8b0646c1242",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_a.biases",
"sha256": "0fe90b738e6ddbcb3994e58554da4445a2c9ceeefd1b6dedafbca9b017c6c585",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 26624,
"groupSize": 64,
"prefix": "language_model.model.layers.9.linear_attn.in_proj_b",
"sha256": "7119a7cb95194fdad192aa1d9f86d3b653aa266e2b2bb04a2f183ba72a2b3b86",
"tensors": [
{
"bytes": 24576,
"dtype": "U32",
"name": "language_model.model.layers.9.linear_attn.in_proj_b.weight",
"sha256": "ddb921f242ee2388c9368a19ff43d8efe168dec2ad3c3d3856d978a9d58eab75",
"shape": [
16,
384
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_b.scales",
"sha256": "916bf9d8799070ca975540d9562aad75dda8d88f01296b90c5a80e04003855c0",
"shape": [
16,
32
]
},
{
"bytes": 1024,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_b.biases",
"sha256": "8c1f3ca9d7cd9d0145ad894ff91e98ee659f018085eeb361fd61fb057b083e78",
"shape": [
16,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.9.linear_attn.in_proj_qkv",
"sha256": "3d83ff23e03bb7c2eee1b7cc326754e8398f39e8d30c760e256fe885fb94e815",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.9.linear_attn.in_proj_qkv.weight",
"sha256": "2329aa76d0c272fee3399d5482487205a59b7d4280e0c33c8985e6508980995d",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_qkv.scales",
"sha256": "5e970d11a7015e0c98789cd90a10c41db91a7fd0f22f9db8f8cb819426855c26",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_qkv.biases",
"sha256": "af34507e8a5a32df422569dc1dfe3569bc92c4bf5311ec1c9f885af2bcf058b6",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.9.linear_attn.in_proj_z",
"sha256": "eaf302d83b4849f106d11890270d48caa132600ff01adab9cfaf10d11eafaf82",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.9.linear_attn.in_proj_z.weight",
"sha256": "367fe7d60a7ceef9434d16ca1ffe682967c04366c529c8a5b9f6d9e99b8ff7df",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_z.scales",
"sha256": "5790a4dd12fdf2ed5ee523d14ad61aa7a1b11b3c293620418c29eb61e24228af",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.in_proj_z.biases",
"sha256": "926fdd94f1994f3d319f6a023c246eb47a4b3f99b099c68040a8ce3070291ca2",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 3407872,
"groupSize": 64,
"prefix": "language_model.model.layers.9.linear_attn.out_proj",
"sha256": "cc659a87162712b253f56df110d5043d0741a756e5058d2f44ed7170ce90e425",
"tensors": [
{
"bytes": 3145728,
"dtype": "U32",
"name": "language_model.model.layers.9.linear_attn.out_proj.weight",
"sha256": "e5ff31532db8c6c0c0f8495616f3fb2cde62ce1da022e701023acdb2284db006",
"shape": [
2048,
384
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.out_proj.scales",
"sha256": "78eac2a498badedf7cf492d61ab37f6580bbb1dac85276655a7d1abe07c8cc79",
"shape": [
2048,
32
]
},
{
"bytes": 131072,
"dtype": "BF16",
"name": "language_model.model.layers.9.linear_attn.out_proj.biases",
"sha256": "9fba5c1682cee551b7db2907c08745ff5f8c33cf31017933ea50c09868b281f6",
"shape": [
2048,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.9.mlp.down_proj",
"sha256": "897a552a3ca37bf531f3291da85f4c0c7bab7a36cb0a791d75b3bf1a53122963",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.9.mlp.down_proj.weight",
"sha256": "9686cc580dd8f51fc1ec19cdfed39d47422486250a62b5a3eaf1b775b87ea890",
"shape": [
2048,
1152
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.down_proj.scales",
"sha256": "317b43787960d1f68a47f4107c3fb4b6f91c99d7b757a001a1b00f7010aa0f79",
"shape": [
2048,
96
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.down_proj.biases",
"sha256": "9be59bcef55af75b492248f0d298d639450db6c3dcc3225dd01c30cb8922bad4",
"shape": [
2048,
96
]
}
]
},
{
"bits": 4,
"bytes": 7077888,
"groupSize": 64,
"prefix": "language_model.model.layers.9.mlp.gate_proj",
"sha256": "d4e532b14cfebbe3898b8c7248b8b277904f52e371321190e546d34efe03801a",
"tensors": [
{
"bytes": 6291456,
"dtype": "U32",
"name": "language_model.model.layers.9.mlp.gate_proj.weight",
"sha256": "2336d27e15a5e97148030310f0350e4b620dd1651cc6780871ed96e942e844db",
"shape": [
6144,
256
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.gate_proj.scales",
"sha256": "ecb0ede2a21fc089830e3bbf6feb438dca08236e57384f00366f09bfd6a291ff",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.gate_proj.biases",
"sha256": "9f62ad7f4910cbb43dcfe201dbc3776766032c6dbf33e39edb1710aa94ebe53c",
"shape": [
6144,
32
]
}
]
},
{
"bits": 6,
"bytes": 10223616,
"groupSize": 64,
"prefix": "language_model.model.layers.9.mlp.up_proj",
"sha256": "64d687bde837af66a03b4a2830723fc0d0afddd51fd2b67328d82805b5fe06fa",
"tensors": [
{
"bytes": 9437184,
"dtype": "U32",
"name": "language_model.model.layers.9.mlp.up_proj.weight",
"sha256": "c86eaf8e9b007c6973ba5da324a1d877ad7742df542d32fda4f1e6f32dd91d01",
"shape": [
6144,
384
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.up_proj.scales",
"sha256": "3129bd158ea8d2fae023b853ec42bf23d5a369d1394a663777f51499d95d2608",
"shape": [
6144,
32
]
},
{
"bytes": 393216,
"dtype": "BF16",
"name": "language_model.model.layers.9.mlp.up_proj.biases",
"sha256": "cd1100550f6a90f5770d70611abf119f3aee7f3329930ff682e34d44e5f9e62a",
"shape": [
6144,
32
]
}
]
}
],
"resolvedMap": {
"language_model.model.embed_tokens": 4,
"language_model.model.layers.0.linear_attn.in_proj_a": 6,
"language_model.model.layers.0.linear_attn.in_proj_b": 6,
"language_model.model.layers.0.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.0.linear_attn.in_proj_z": 6,
"language_model.model.layers.0.linear_attn.out_proj": 6,
"language_model.model.layers.0.mlp.down_proj": 6,
"language_model.model.layers.0.mlp.gate_proj": 4,
"language_model.model.layers.0.mlp.up_proj": 6,
"language_model.model.layers.1.linear_attn.in_proj_a": 6,
"language_model.model.layers.1.linear_attn.in_proj_b": 6,
"language_model.model.layers.1.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.1.linear_attn.in_proj_z": 6,
"language_model.model.layers.1.linear_attn.out_proj": 6,
"language_model.model.layers.1.mlp.down_proj": 6,
"language_model.model.layers.1.mlp.gate_proj": 4,
"language_model.model.layers.1.mlp.up_proj": 6,
"language_model.model.layers.10.linear_attn.in_proj_a": 6,
"language_model.model.layers.10.linear_attn.in_proj_b": 6,
"language_model.model.layers.10.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.10.linear_attn.in_proj_z": 6,
"language_model.model.layers.10.linear_attn.out_proj": 6,
"language_model.model.layers.10.mlp.down_proj": 6,
"language_model.model.layers.10.mlp.gate_proj": 4,
"language_model.model.layers.10.mlp.up_proj": 6,
"language_model.model.layers.11.mlp.down_proj": 6,
"language_model.model.layers.11.mlp.gate_proj": 4,
"language_model.model.layers.11.mlp.up_proj": 6,
"language_model.model.layers.11.self_attn.k_proj": 6,
"language_model.model.layers.11.self_attn.o_proj": 6,
"language_model.model.layers.11.self_attn.q_proj": 6,
"language_model.model.layers.11.self_attn.v_proj": 6,
"language_model.model.layers.12.linear_attn.in_proj_a": 6,
"language_model.model.layers.12.linear_attn.in_proj_b": 6,
"language_model.model.layers.12.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.12.linear_attn.in_proj_z": 6,
"language_model.model.layers.12.linear_attn.out_proj": 6,
"language_model.model.layers.12.mlp.down_proj": 6,
"language_model.model.layers.12.mlp.gate_proj": 4,
"language_model.model.layers.12.mlp.up_proj": 6,
"language_model.model.layers.13.linear_attn.in_proj_a": 6,
"language_model.model.layers.13.linear_attn.in_proj_b": 6,
"language_model.model.layers.13.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.13.linear_attn.in_proj_z": 6,
"language_model.model.layers.13.linear_attn.out_proj": 6,
"language_model.model.layers.13.mlp.down_proj": 6,
"language_model.model.layers.13.mlp.gate_proj": 4,
"language_model.model.layers.13.mlp.up_proj": 6,
"language_model.model.layers.14.linear_attn.in_proj_a": 6,
"language_model.model.layers.14.linear_attn.in_proj_b": 6,
"language_model.model.layers.14.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.14.linear_attn.in_proj_z": 6,
"language_model.model.layers.14.linear_attn.out_proj": 6,
"language_model.model.layers.14.mlp.down_proj": 6,
"language_model.model.layers.14.mlp.gate_proj": 4,
"language_model.model.layers.14.mlp.up_proj": 6,
"language_model.model.layers.15.mlp.down_proj": 6,
"language_model.model.layers.15.mlp.gate_proj": 4,
"language_model.model.layers.15.mlp.up_proj": 6,
"language_model.model.layers.15.self_attn.k_proj": 6,
"language_model.model.layers.15.self_attn.o_proj": 6,
"language_model.model.layers.15.self_attn.q_proj": 6,
"language_model.model.layers.15.self_attn.v_proj": 6,
"language_model.model.layers.16.linear_attn.in_proj_a": 6,
"language_model.model.layers.16.linear_attn.in_proj_b": 6,
"language_model.model.layers.16.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.16.linear_attn.in_proj_z": 6,
"language_model.model.layers.16.linear_attn.out_proj": 6,
"language_model.model.layers.16.mlp.down_proj": 6,
"language_model.model.layers.16.mlp.gate_proj": 4,
"language_model.model.layers.16.mlp.up_proj": 6,
"language_model.model.layers.17.linear_attn.in_proj_a": 6,
"language_model.model.layers.17.linear_attn.in_proj_b": 6,
"language_model.model.layers.17.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.17.linear_attn.in_proj_z": 6,
"language_model.model.layers.17.linear_attn.out_proj": 6,
"language_model.model.layers.17.mlp.down_proj": 6,
"language_model.model.layers.17.mlp.gate_proj": 4,
"language_model.model.layers.17.mlp.up_proj": 6,
"language_model.model.layers.18.linear_attn.in_proj_a": 6,
"language_model.model.layers.18.linear_attn.in_proj_b": 6,
"language_model.model.layers.18.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.18.linear_attn.in_proj_z": 6,
"language_model.model.layers.18.linear_attn.out_proj": 6,
"language_model.model.layers.18.mlp.down_proj": 6,
"language_model.model.layers.18.mlp.gate_proj": 4,
"language_model.model.layers.18.mlp.up_proj": 6,
"language_model.model.layers.19.mlp.down_proj": 6,
"language_model.model.layers.19.mlp.gate_proj": 4,
"language_model.model.layers.19.mlp.up_proj": 6,
"language_model.model.layers.19.self_attn.k_proj": 6,
"language_model.model.layers.19.self_attn.o_proj": 6,
"language_model.model.layers.19.self_attn.q_proj": 6,
"language_model.model.layers.19.self_attn.v_proj": 6,
"language_model.model.layers.2.linear_attn.in_proj_a": 6,
"language_model.model.layers.2.linear_attn.in_proj_b": 6,
"language_model.model.layers.2.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.2.linear_attn.in_proj_z": 6,
"language_model.model.layers.2.linear_attn.out_proj": 6,
"language_model.model.layers.2.mlp.down_proj": 6,
"language_model.model.layers.2.mlp.gate_proj": 4,
"language_model.model.layers.2.mlp.up_proj": 6,
"language_model.model.layers.20.linear_attn.in_proj_a": 6,
"language_model.model.layers.20.linear_attn.in_proj_b": 6,
"language_model.model.layers.20.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.20.linear_attn.in_proj_z": 6,
"language_model.model.layers.20.linear_attn.out_proj": 6,
"language_model.model.layers.20.mlp.down_proj": 6,
"language_model.model.layers.20.mlp.gate_proj": 4,
"language_model.model.layers.20.mlp.up_proj": 6,
"language_model.model.layers.21.linear_attn.in_proj_a": 6,
"language_model.model.layers.21.linear_attn.in_proj_b": 6,
"language_model.model.layers.21.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.21.linear_attn.in_proj_z": 6,
"language_model.model.layers.21.linear_attn.out_proj": 6,
"language_model.model.layers.21.mlp.down_proj": 6,
"language_model.model.layers.21.mlp.gate_proj": 4,
"language_model.model.layers.21.mlp.up_proj": 6,
"language_model.model.layers.22.linear_attn.in_proj_a": 6,
"language_model.model.layers.22.linear_attn.in_proj_b": 6,
"language_model.model.layers.22.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.22.linear_attn.in_proj_z": 6,
"language_model.model.layers.22.linear_attn.out_proj": 6,
"language_model.model.layers.22.mlp.down_proj": 6,
"language_model.model.layers.22.mlp.gate_proj": 4,
"language_model.model.layers.22.mlp.up_proj": 6,
"language_model.model.layers.23.mlp.down_proj": 6,
"language_model.model.layers.23.mlp.gate_proj": 4,
"language_model.model.layers.23.mlp.up_proj": 6,
"language_model.model.layers.23.self_attn.k_proj": 6,
"language_model.model.layers.23.self_attn.o_proj": 6,
"language_model.model.layers.23.self_attn.q_proj": 6,
"language_model.model.layers.23.self_attn.v_proj": 6,
"language_model.model.layers.3.mlp.down_proj": 6,
"language_model.model.layers.3.mlp.gate_proj": 4,
"language_model.model.layers.3.mlp.up_proj": 6,
"language_model.model.layers.3.self_attn.k_proj": 6,
"language_model.model.layers.3.self_attn.o_proj": 6,
"language_model.model.layers.3.self_attn.q_proj": 6,
"language_model.model.layers.3.self_attn.v_proj": 6,
"language_model.model.layers.4.linear_attn.in_proj_a": 6,
"language_model.model.layers.4.linear_attn.in_proj_b": 6,
"language_model.model.layers.4.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.4.linear_attn.in_proj_z": 6,
"language_model.model.layers.4.linear_attn.out_proj": 6,
"language_model.model.layers.4.mlp.down_proj": 6,
"language_model.model.layers.4.mlp.gate_proj": 4,
"language_model.model.layers.4.mlp.up_proj": 6,
"language_model.model.layers.5.linear_attn.in_proj_a": 6,
"language_model.model.layers.5.linear_attn.in_proj_b": 6,
"language_model.model.layers.5.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.5.linear_attn.in_proj_z": 6,
"language_model.model.layers.5.linear_attn.out_proj": 6,
"language_model.model.layers.5.mlp.down_proj": 6,
"language_model.model.layers.5.mlp.gate_proj": 4,
"language_model.model.layers.5.mlp.up_proj": 6,
"language_model.model.layers.6.linear_attn.in_proj_a": 6,
"language_model.model.layers.6.linear_attn.in_proj_b": 6,
"language_model.model.layers.6.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.6.linear_attn.in_proj_z": 6,
"language_model.model.layers.6.linear_attn.out_proj": 6,
"language_model.model.layers.6.mlp.down_proj": 6,
"language_model.model.layers.6.mlp.gate_proj": 4,
"language_model.model.layers.6.mlp.up_proj": 6,
"language_model.model.layers.7.mlp.down_proj": 6,
"language_model.model.layers.7.mlp.gate_proj": 4,
"language_model.model.layers.7.mlp.up_proj": 6,
"language_model.model.layers.7.self_attn.k_proj": 6,
"language_model.model.layers.7.self_attn.o_proj": 6,
"language_model.model.layers.7.self_attn.q_proj": 6,
"language_model.model.layers.7.self_attn.v_proj": 6,
"language_model.model.layers.8.linear_attn.in_proj_a": 6,
"language_model.model.layers.8.linear_attn.in_proj_b": 6,
"language_model.model.layers.8.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.8.linear_attn.in_proj_z": 6,
"language_model.model.layers.8.linear_attn.out_proj": 6,
"language_model.model.layers.8.mlp.down_proj": 6,
"language_model.model.layers.8.mlp.gate_proj": 4,
"language_model.model.layers.8.mlp.up_proj": 6,
"language_model.model.layers.9.linear_attn.in_proj_a": 6,
"language_model.model.layers.9.linear_attn.in_proj_b": 6,
"language_model.model.layers.9.linear_attn.in_proj_qkv": 6,
"language_model.model.layers.9.linear_attn.in_proj_z": 6,
"language_model.model.layers.9.linear_attn.out_proj": 6,
"language_model.model.layers.9.mlp.down_proj": 6,
"language_model.model.layers.9.mlp.gate_proj": 4,
"language_model.model.layers.9.mlp.up_proj": 6
},
"resolvedMapSHA256": "546173ac4d0177c95b621209ec279d0d5e5c6677c3011314f8e94010b5f8c2c5",
"widthTotals": {
"q4": {
"bytes": 283115520,
"prefixCount": 25,
"tensorCount": 75
},
"q6": {
"bytes": 869965824,
"prefixCount": 162,
"tensorCount": 486
}
}
},
"schemaVersion": 2,
"source": {
"identifier": "mini-96k-mixed46b-dwq-dflash",
"local": true
},
"tokenizerSHA256": "a327311621c5780b2261e24005fc7b7adf271300594d8e502761cdeb944b0d6c",
"tokenizerValidation": {
"passed": null,
"runtime": "none"
},
"validation": {
"passed": null,
"runtime": "none"
}
}